Recent advancements in 3D reconstruction from single images have been driven by the evolution of generative models. Prominent among these are methods based on Score Distillation Sampling (SDS) and the adaptation of diffusion models in the 3D domain. Despite their progress, these techniques often face limitations due to slow optimization or rendering processes, leading to extensive training and optimization times. In this paper, we introduce a novel approach for single-view reconstruction that efficiently generates a 3D model from a single image via feed-forward inference. Our method utilizes two transformer-based networks, namely a point decoder and a triplane decoder, to reconstruct 3D objects using a hybrid Triplane-Gaussian intermediate representation. This hybrid representation strikes a balance, achieving a faster rendering speed compared to implicit representations while simultaneously delivering superior rendering quality than explicit representations. The point decoder is designed for generating point clouds from single images, offering an explicit representation which is then utilized by the triplane decoder to query Gaussian features for each point. This design choice addresses the challenges associated with directly regressing explicit 3D Gaussian attributes characterized by their non-structural nature. Subsequently, the 3D Gaussians are decoded by an MLP to enable rapid rendering through splatting. Both decoders are built upon a scalable, transformer-based architecture and have been efficiently trained on large-scale 3D datasets. The evaluations conducted on both synthetic datasets and real-world images demonstrate that our method not only achieves higher quality but also ensures a faster runtime in comparison to previous state-of-the-art techniques. Please see our project page at https://zouzx.github.io/TriplaneGaussian/.
Research into dynamic 3D scene understanding has primarily focused on short-term change tracking from dense observations, while little attention has been paid to long-term changes with sparse observations. We address this gap with MoRE, a novel approach for multi-object relocalization and reconstruction in evolving environments. We view these environments as "living scenes" and consider the problem of transforming scans taken at different points in time into a 3D reconstruction of the object instances, whose accuracy and completeness increase over time. At the core of our method lies an SE(3)-equivariant representation in a single encoder-decoder network, trained on synthetic data. This representation enables us to seamlessly tackle instance matching, registration, and reconstruction. We also introduce a joint optimization algorithm that facilitates the accumulation of point clouds originating from the same instance across multiple scans taken at different points in time. We validate our method on synthetic and real-world data and demonstrate state-of-the-art performance in both end-to-end performance and individual subtasks.
We present a unified, promptable model capable of simultaneously segmenting, recognizing, and captioning anything. Unlike SAM, we aim to build a versatile region representation in the wild via visual prompting. To achieve this, we train a generalizable model with massive segmentation masks, \eg, SA-1B masks, and semantic priors from a pre-trained CLIP model with 5 billion parameters. Specifically, we construct a promptable image decoder by adding a semantic token to each mask token. The semantic token is responsible for learning the semantic priors in a predefined concept space. Through joint optimization of segmentation on mask tokens and concept prediction on semantic tokens, our model exhibits strong regional recognition and localization capabilities. For example, an additional 38M-parameter causal text decoder trained from scratch sets a new record with a CIDEr score of 164.7 on the Visual Genome region captioning task. We believe this model can be a versatile region-level image tokenizer, capable of encoding general-purpose region context for a broad range of visual perception tasks. Code and models are available at {\footnotesize \url{https://github.com/baaivision/tokenize-anything}}.
Deep graph convolution networks (GCNs) have recently shown excellent performance in traffic prediction tasks. However, they face some challenges. First, few existing models consider the influence of auxiliary information, i.e., weather and holidays, which may result in a poor grasp of spatial-temporal dynamics of traffic data. Second, both the construction of a dynamic adjacent matrix and regular graph convolution operations have quadratic computation complexity, which restricts the scalability of GCN-based models. To address such challenges, this work proposes a deep encoder-decoder model entitled AIMSAN. It contains an auxiliary information-aware module (AIM) and sparse cross attention-based graph convolution network (SAN). The former learns multi-attribute auxiliary information and obtains its embedded presentation of different time-window sizes. The latter uses a cross-attention mechanism to construct dynamic adjacent matrices by fusing traffic data and embedded auxiliary data. Then, SAN applies diffusion GCN on traffic data to mine rich spatial-temporal dynamics. Furthermore, AIMSAN considers and uses the spatial sparseness of traffic nodes to reduce the quadratic computation complexity. Experimental results on three public traffic datasets demonstrate that the proposed method outperforms other counterparts in terms of various performance indices. Specifically, the proposed method has competitive performance with the state-of-the-art algorithms but saves 35.74% of GPU memory usage, 42.25% of training time, and 45.51% of validation time on average.
This study presents a deep learning-based approach to seismic velocity inversion problem, focusing on both noisy and noiseless training datasets of varying sizes. Our Seismic Velocity Inversion Network (SVInvNet) introduces a novel architecture that contains a multi-connection encoder-decoder structure enhanced with dense blocks. This design is specifically tuned to effectively process time series data, which is essential for addressing the challenges of non-linear seismic velocity inversion. For training and testing, we created diverse seismic velocity models, including multi-layered, faulty, and salt dome categories. We also investigated how different kinds of ambient noise, both coherent and stochastic, and the size of the training dataset affect learning outcomes. SVInvNet is trained on datasets ranging from 750 to 6,000 samples and is tested using a large benchmark dataset of 12,000 samples. Despite its fewer parameters compared to the baseline model, SVInvNet achieves superior performance with this dataset. The performance of SVInvNet was further evaluated using the OpenFWI dataset and Marmousi-derived velocity models. The comparative analysis clearly reveals the effectiveness of the proposed model.
We introduce a novel task of 3D visual grounding in monocular RGB images using language descriptions with both appearance and geometry information. Specifically, we build a large-scale dataset, Mono3DRefer, which contains 3D object targets with their corresponding geometric text descriptions, generated by ChatGPT and refined manually. To foster this task, we propose Mono3DVG-TR, an end-to-end transformer-based network, which takes advantage of both the appearance and geometry information in text embeddings for multi-modal learning and 3D object localization. Depth predictor is designed to explicitly learn geometry features. The dual text-guided adapter is proposed to refine multiscale visual and geometry features of the referred object. Based on depth-text-visual stacking attention, the decoder fuses object-level geometric cues and visual appearance into a learnable query. Comprehensive benchmarks and some insightful analyses are provided for Mono3DVG. Extensive comparisons and ablation studies show that our method significantly outperforms all baselines. The dataset and code will be publicly available at: https://github.com/ZhanYang-nwpu/Mono3DVG.
Haze obscures remote sensing images, hindering valuable information extraction. To this end, we propose RSHazeNet, an encoder-minimal and decoder-minimal framework for efficient remote sensing image dehazing. Specifically, regarding the process of merging features within the same level, we develop an innovative module called intra-level transposed fusion module (ITFM). This module employs adaptive transposed self-attention to capture comprehensive context-aware information, facilitating the robust context-aware feature fusion. Meanwhile, we present a cross-level multi-view interaction module (CMIM) to enable effective interactions between features from various levels, mitigating the loss of information due to the repeated sampling operations. In addition, we propose a multi-view progressive extraction block (MPEB) that partitions the features into four distinct components and employs convolution with varying kernel sizes, groups, and dilation factors to facilitate view-progressive feature learning. Extensive experiments demonstrate the superiority of our proposed RSHazeNet. We release the source code and all pre-trained models at \url{https://github.com/chdwyb/RSHazeNet}.
Reliable object grasping is a crucial capability for autonomous robots. However, many existing grasping approaches focus on general clutter removal without explicitly modeling objects and thus only relying on the visible local geometry. We introduce CenterGrasp, a novel framework that combines object awareness and holistic grasping. CenterGrasp learns a general object prior by encoding shapes and valid grasps in a continuous latent space. It consists of an RGB-D image encoder that leverages recent advances to detect objects and infer their pose and latent code, and a decoder to predict shape and grasps for each object in the scene. We perform extensive experiments on simulated as well as real-world cluttered scenes and demonstrate strong scene reconstruction and 6-DoF grasp-pose estimation performance. Compared to the state of the art, CenterGrasp achieves an improvement of 38.5 mm in shape reconstruction and 33 percentage points on average in grasp success. We make the code and trained models publicly available at http://centergrasp.cs.uni-freiburg.de.
Structured data, which constitutes a significant portion of existing data types, has been a long-standing research topic in the field of machine learning. Various representation learning methods for tabular data have been proposed, ranging from encoder-decoder structures to Transformers. Among these, Transformer-based methods have achieved state-of-the-art performance not only in tabular data but also in various other fields, including computer vision and natural language processing. However, recent studies have revealed that self-attention, a key component of Transformers, can lead to an oversmoothing issue. We show that Transformers for tabular data also face this problem, and to address the problem, we propose a novel matrix polynomial-based self-attention layer as a substitute for the original self-attention layer, which enhances model scalability. In our experiments with three representative table learning models equipped with our proposed layer, we illustrate that the layer effectively mitigates the oversmoothing problem and enhances the representation performance of the existing methods, outperforming the state-of-the-art table representation methods.
This study describes our system for Task 1 Single-speaker Visual Speech Recognition (VSR) fixed track in the Chinese Continuous Visual Speech Recognition Challenge (CNVSRC) 2023. Specifically, we use intermediate connectionist temporal classification (Inter CTC) residual modules to relax the conditional independence assumption of CTC in our model. Then we use a bi-transformer decoder to enable the model to capture both past and future contextual information. In addition, we use Chinese characters as the modeling units to improve the recognition accuracy of our model. Finally, we use a recurrent neural network language model (RNNLM) for shallow fusion in the inference stage. Experiments show that our system achieves a character error rate (CER) of 38.09% on the Eval set which reaches a relative CER reduction of 21.63% over the official baseline, and obtains a second place in the challenge.
Diffusion models have achieved great success in modeling continuous data modalities such as images, audio, and video, but have seen limited use in discrete domains such as language. Recent attempts to adapt diffusion to language have presented diffusion as an alternative to existing pretrained language models. We view diffusion and existing language models as complementary. We demonstrate that encoder-decoder language models can be utilized to efficiently learn high-quality language autoencoders. We then demonstrate that continuous diffusion models can be learned in the latent space of the language autoencoder, enabling us to sample continuous latent representations that can be decoded into natural language with the pretrained decoder. We validate the effectiveness of our approach for unconditional, class-conditional, and sequence-to-sequence language generation. We demonstrate across multiple diverse data sets that our latent language diffusion models are significantly more effective than previous diffusion language models.
The ability to provide fine-grained control for generating and editing visual imagery has profound implications for computer vision and its applications. Previous works have explored extending controllability in two directions: instruction tuning with text-based prompts and multi-modal conditioning. However, these works make one or more unnatural assumptions on the number and/or type of modality inputs used to express controllability. We propose InstructAny2Pix, a flexible multi-modal instruction-following system that enables users to edit an input image using instructions involving audio, images, and text. InstructAny2Pix consists of three building blocks that facilitate this capability: a multi-modal encoder that encodes different modalities such as images and audio into a unified latent space, a diffusion model that learns to decode representations in this latent space into images, and a multi-modal LLM that can understand instructions involving multiple images and audio pieces and generate a conditional embedding of the desired output, which can be used by the diffusion decoder. Additionally, to facilitate training efficiency and improve generation quality, we include an additional refinement prior module that enhances the visual quality of LLM outputs. These designs are critical to the performance of our system. We demonstrate that our system can perform a series of novel instruction-guided editing tasks. The code is available at https://github.com/jacklishufan/InstructAny2Pix.git
Recently, a few open-vocabulary methods have been proposed by employing a unified architecture to tackle generic segmentation and detection tasks. However, their performance still lags behind the task-specific models due to the conflict between different tasks, and their open-vocabulary capability is limited due to the inadequate use of CLIP. To address these challenges, we present a universal transformer-based framework, abbreviated as OpenSD, which utilizes the same architecture and network parameters to handle open-vocabulary segmentation and detection tasks. First, we introduce a decoder decoupled learning strategy to alleviate the semantic conflict between thing and staff categories so that each individual task can be learned more effectively under the same framework. Second, to better leverage CLIP for end-to-end segmentation and detection, we propose dual classifiers to handle the in-vocabulary domain and out-of-vocabulary domain, respectively. The text encoder is further trained to be region-aware for both thing and stuff categories through decoupled prompt learning, enabling them to filter out duplicated and low-quality predictions, which is important to end-to-end segmentation and detection. Extensive experiments are conducted on multiple datasets under various circumstances. The results demonstrate that OpenSD outperforms state-of-the-art open-vocabulary segmentation and detection methods in both closed- and open-vocabulary settings. Code is available at https://github.com/strongwolf/OpenSD
In this paper, we introduce Recon3DMind, an innovative task aimed at reconstructing 3D visuals from Functional Magnetic Resonance Imaging (fMRI) signals, marking a significant advancement in the fields of cognitive neuroscience and computer vision. To support this pioneering task, we present the fMRI-Shape dataset, which includes data from 14 participants and features 360-degree videos of 3D objects to enable comprehensive fMRI signal capture across various settings, thereby laying a foundation for future research. Furthermore, we propose MinD-3D, a novel and effective three-stage framework specifically designed to decode the brain's 3D visual information from fMRI signals, demonstrating the feasibility of this challenging task. The framework begins by extracting and aggregating features from fMRI frames through a neuro-fusion encoder, subsequently employs a feature bridge diffusion model to generate visual features, and ultimately recovers the 3D object via a generative transformer decoder. We assess the performance of MinD-3D using a suite of semantic and structural metrics and analyze the correlation between the features extracted by our model and the visual regions of interest (ROIs) in fMRI signals. Our findings indicate that MinD-3D not only reconstructs 3D objects with high semantic relevance and spatial similarity but also significantly enhances our understanding of the human brain's capabilities in processing 3D visual information. Project page at: https://jianxgao.github.io/MinD-3D.
Video captioning in Nepali, a language written in the Devanagari script, presents a unique challenge due to the lack of existing academic work in this domain. This work develops a novel encoder-decoder paradigm for Nepali video captioning to tackle this difficulty. LSTM and GRU sequence-to-sequence models are used in the model to produce related textual descriptions based on features retrieved from video frames using CNNs. Using Google Translate and manual post-editing, a Nepali video captioning dataset is generated from the Microsoft Research Video Description Corpus (MSVD) dataset created using Google Translate, and manual post-editing work. The efficiency of the model for Devanagari-scripted video captioning is demonstrated by BLEU, METOR, and ROUGE measures, which are used to assess its performance.
Visual synthesis has recently seen significant leaps in performance, largely due to breakthroughs in generative models. Diffusion models have been a key enabler, as they excel in image diversity. However, this comes at the cost of slow training and synthesis, which is only partially alleviated by latent diffusion. To this end, flow matching is an appealing approach due to its complementary characteristics of faster training and inference but less diverse synthesis. We demonstrate that introducing flow matching between a frozen diffusion model and a convolutional decoder enables high-resolution image synthesis at reduced computational cost and model size. A small diffusion model can then effectively provide the necessary visual diversity, while flow matching efficiently enhances resolution and detail by mapping the small to a high-dimensional latent space. These latents are then projected to high-resolution images by the subsequent convolutional decoder of the latent diffusion approach. Combining the diversity of diffusion models, the efficiency of flow matching, and the effectiveness of convolutional decoders, state-of-the-art high-resolution image synthesis is achieved at $1024^2$ pixels with minimal computational cost. Further scaling up our method we can reach resolutions up to $2048^2$ pixels. Importantly, our approach is orthogonal to recent approximation and speed-up strategies for the underlying model, making it easily integrable into the various diffusion model frameworks.
Foundation models possess strong capabilities in reasoning and memorizing across modalities. To further unleash the power of foundation models, we present FIND, a generalized interface for aligning foundation models' embeddings with unified image and dataset-level understanding spanning modality and granularity. As shown in the teaser figure, a lightweight transformer interface without tuning any foundation model weights is enough for segmentation, grounding, and retrieval in an interleaved manner. The proposed interface has the following favorable attributes: (1) Generalizable. It applies to various tasks spanning retrieval, segmentation, etc., under the same architecture and weights. (2) Interleavable. With the benefit of multi-task multi-modal training, the proposed interface creates an interleaved shared embedding space. (3) Extendable. The proposed interface is adaptive to new tasks, and new models. In light of the interleaved embedding space, we introduce FIND-Bench, which introduces new training and evaluation annotations to the COCO dataset for interleaved segmentation and retrieval. We are the first work aligning foundations models' embeddings for interleave understanding. Meanwhile, our approach achieves state-of-the-art performance on FIND-Bench and competitive performance on standard retrieval and segmentation settings.
Canonical relation extraction aims to extract relational triples from sentences, where the triple elements (entity pairs and their relationship) are mapped to the knowledge base. Recently, methods based on the encoder-decoder architecture are proposed and achieve promising results. However, these methods cannot well utilize the entity information, which is merely used as augmented training data. Moreover, they are incapable of representing novel entities, since no embeddings have been learned for them. In this paper, we propose a novel framework, Bi-Encoder-Decoder (BED), to solve the above issues. Specifically, to fully utilize entity information, we employ an encoder to encode semantics of this information, leading to high-quality entity representations. For novel entities, given a trained entity encoder, their representations can be easily generated. Experimental results on two datasets show that, our method achieves a significant performance improvement over the previous state-of-the-art and handle novel entities well without retraining.
This article presents a transformer and convolutional neural network (CNN) hybrid deep neural network for semantic segmentation of very high resolution (VHR) remote sensing imagery. The model follows an encoder–decoder structure. The encoder module uses a new universal backbone Swin transformer to extract features to achieve better long-range spatial dependencies modeling. The decoder module draws on some effective blocks and successful strategies of CNN-based models in remote sensing image segmentation. In the middle of the framework, an atrous spatial pyramid pooling block based on depthwise separable convolution (SASPP) is applied to obtain a multiscale context. A U-shaped decoder is used to gradually restore the size of the feature maps. Three skip connections are built between the encoder and decoder feature maps of the same size to maintain the transmission of local details and enhance the communication of multiscale features. A squeeze-and-excitation (SE) channel attention block is added before segmentation for feature augmentation. An auxiliary boundary detection branch is combined to provide edge constraints for semantic segmentation. Extensive ablation experiments were conducted on the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen and Potsdam benchmarks to test the effectiveness of multiple components of the network. At the same time, the proposed method is compared with the current state-of-the-art methods on the two benchmarks. The proposed hybrid network achieved the second highest overall accuracy (OA) on both the Potsdam and Vaihingen benchmarks (code and models are available at https://github.com/zq7734509/mmsegmentation- multilayer).
The hydrometric prediction of water quantity is useful for a variety of applications, including water management, flood forecasting, and flood control. However, the task is difficult due to the dynamic nature and limited data of water systems. Highly interconnected water systems can significantly affect hydrometric forecasting. Consequently, it is crucial to develop models that represent the relationships between other system components. In recent years, numerous hydrological applications have been studied, including streamflow prediction, flood forecasting, and water quality prediction. Existing methods are unable to model the influence of adjacent regions between pairs of variables. In this paper, we propose a spatiotemporal forecasting model that augments the hidden state in Graph Convolution Recurrent Neural Network (GCRN) encoder-decoder using an efficient version of the attention mechanism. The attention layer allows the decoder to access different parts of the input sequence selectively. Since water systems are interconnected and the connectivity information between the stations is implicit, the proposed model leverages a graph learning module to extract a sparse graph adjacency matrix adaptively based on the data. Spatiotemporal forecasting relies on historical data. In some regions, however, historical data may be limited or incomplete, making it difficult to accurately predict future water conditions. Further, we present a new benchmark dataset of water flow from a network of Canadian stations on rivers, streams, and lakes. Experimental results demonstrate that our proposed model TransGlow significantly outperforms baseline methods by a wide margin.