We tackle the problem of monocular 3D object detection across different sensors, environments, and camera setups. In this paper, we introduce a novel unsupervised domain adaptation approach, MonoCT, that generates highly accurate pseudo labels for self-supervision. Inspired by our observation that accurate depth estimation is critical to mitigating domain shifts, MonoCT introduces a novel Generalized Depth Enhancement (GDE) module with an ensemble concept to improve depth estimation accuracy. Moreover, we introduce a novel Pseudo Label Scoring (PLS) module by exploring inner-model consistency measurement and a Diversity Maximization (DM) strategy to further generate high-quality pseudo labels for self-training. Extensive experiments on six benchmarks show that MonoCT outperforms existing SOTA domain adaptation methods by large margins (~21% minimum for AP Mod.) and generalizes well to car, traffic camera and drone views.
Photo-realistic rendering and novel view synthesis play a crucial role in human-computer interaction tasks, from gaming to path planning. Neural Radiance Fields (NeRFs) model scenes as continuous volumetric functions and achieve remarkable rendering quality. However, NeRFs often struggle in large, low-textured areas, producing cloudy artifacts known as ''floaters'' that reduce scene realism, especially in indoor environments with featureless architectural surfaces like walls, ceilings, and floors. To overcome this limitation, prior work has integrated geometric constraints into the NeRF pipeline, typically leveraging depth information derived from Structure from Motion or Multi-View Stereo. Yet, conventional RGB-feature correspondence methods face challenges in accurately estimating depth in textureless regions, leading to unreliable constraints. This challenge is further complicated in 360-degree ''inside-out'' views, where sparse visual overlap between adjacent images further hinders depth estimation. In order to address these issues, we propose an efficient and robust method for computing dense depth priors, specifically tailored for large low-textured architectural surfaces in indoor environments. We introduce a novel depth loss function to enhance rendering quality in these challenging, low-feature regions, while complementary depth-patch regularization further refines depth consistency across other areas. Experiments with Instant-NGP on two synthetic 360-degree indoor scenes demonstrate improved visual fidelity with our method compared to standard photometric loss and Mean Squared Error depth supervision.
We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters, point maps, depth maps, and 3D point tracks, from one, a few, or hundreds of its views. This approach is a step forward in 3D computer vision, where models have typically been constrained to and specialized for single tasks. It is also simple and efficient, reconstructing images in under one second, and still outperforming alternatives that require post-processing with visual geometry optimization techniques. The network achieves state-of-the-art results in multiple 3D tasks, including camera parameter estimation, multi-view depth estimation, dense point cloud reconstruction, and 3D point tracking. We also show that using pretrained VGGT as a feature backbone significantly enhances downstream tasks, such as non-rigid point tracking and feed-forward novel view synthesis. Code and models are publicly available at https://github.com/facebookresearch/vggt.
Transparent objects are common in daily life, and understanding their multi-layer depth information -- perceiving both the transparent surface and the objects behind it -- is crucial for real-world applications that interact with transparent materials. In this paper, we introduce LayeredDepth, the first dataset with multi-layer depth annotations, including a real-world benchmark and a synthetic data generator, to support the task of multi-layer depth estimation. Our real-world benchmark consists of 1,500 images from diverse scenes, and evaluating state-of-the-art depth estimation methods on it reveals that they struggle with transparent objects. The synthetic data generator is fully procedural and capable of providing training data for this task with an unlimited variety of objects and scene compositions. Using this generator, we create a synthetic dataset with 15,300 images. Baseline models training solely on this synthetic dataset produce good cross-domain multi-layer depth estimation. Fine-tuning state-of-the-art single-layer depth models on it substantially improves their performance on transparent objects, with quadruplet accuracy on our benchmark increased from 55.14% to 75.20%. All images and validation annotations are available under CC0 at https://layereddepth.cs.princeton.edu.
Many studies utilize dual-pixel (DP) sensor phase characteristics for various applications, such as depth estimation and deblurring. However, since the DP image features are entirely determined by the camera hardware, DP-depth paired datasets are very scarce, especially when performing depth estimation on customized cameras. To overcome this, studies simulate DP images using ideal optical system models. However, these simulations often violate real optical propagation laws,leading to poor generalization to real DP data. To address this, we investigate the domain gap between simulated and real DP data, and propose solutions using the Simulating DP images from ray tracing (Sdirt) scheme. The Sdirt generates realistic DP images via ray tracing and integrates them into the depth estimation training pipeline. Experimental results show that models trained with Sdirt-simulated images generalize better to real DP data.
Learning accurate scene reconstruction without pose priors in neural radiance fields is challenging due to inherent geometric ambiguity. Recent development either relies on correspondence priors for regularization or uses off-the-shelf flow estimators to derive analytical poses. However, the potential for jointly learning scene geometry, camera poses, and dense flow within a unified neural representation remains largely unexplored. In this paper, we present Flow-NeRF, a unified framework that simultaneously optimizes scene geometry, camera poses, and dense optical flow all on-the-fly. To enable the learning of dense flow within the neural radiance field, we design and build a bijective mapping for flow estimation, conditioned on pose. To make the scene reconstruction benefit from the flow estimation, we develop an effective feature enhancement mechanism to pass canonical space features to world space representations, significantly enhancing scene geometry. We validate our model across four important tasks, i.e., novel view synthesis, depth estimation, camera pose prediction, and dense optical flow estimation, using several datasets. Our approach surpasses previous methods in almost all metrics for novel-view view synthesis and depth estimation and yields both qualitatively sound and quantitatively accurate novel-view flow. Our project page is https://zhengxunzhi.github.io/flownerf/.
We introduce \textit{WonderVerse}, a simple but effective framework for generating extendable 3D scenes. Unlike existing methods that rely on iterative depth estimation and image inpainting, often leading to geometric distortions and inconsistencies, WonderVerse leverages the powerful world-level priors embedded within video generative foundation models to create highly immersive and geometrically coherent 3D environments. Furthermore, we propose a new technique for controllable 3D scene extension to substantially increase the scale of the generated environments. Besides, we introduce a novel abnormal sequence detection module that utilizes camera trajectory to address geometric inconsistency in the generated videos. Finally, WonderVerse is compatible with various 3D reconstruction methods, allowing both efficient and high-quality generation. Extensive experiments on 3D scene generation demonstrate that our WonderVerse, with an elegant and simple pipeline, delivers extendable and highly-realistic 3D scenes, markedly outperforming existing works that rely on more complex architectures.
We introduce GarmentCrafter, a new approach that enables non-professional users to create and modify 3D garments from a single-view image. While recent advances in image generation have facilitated 2D garment design, creating and editing 3D garments remains challenging for non-professional users. Existing methods for single-view 3D reconstruction often rely on pre-trained generative models to synthesize novel views conditioning on the reference image and camera pose, yet they lack cross-view consistency, failing to capture the internal relationships across different views. In this paper, we tackle this challenge through progressive depth prediction and image warping to approximate novel views. Subsequently, we train a multi-view diffusion model to complete occluded and unknown clothing regions, informed by the evolving camera pose. By jointly inferring RGB and depth, GarmentCrafter enforces inter-view coherence and reconstructs precise geometries and fine details. Extensive experiments demonstrate that our method achieves superior visual fidelity and inter-view coherence compared to state-of-the-art single-view 3D garment reconstruction methods.
In tomato greenhouse, phenotypic measurement is meaningful for researchers and farmers to monitor crop growth, thereby precisely control environmental conditions in time, leading to better quality and higher yield. Traditional phenotyping mainly relies on manual measurement, which is accurate but inefficient, more importantly, endangering the health and safety of people. Several studies have explored computer vision-based methods to replace manual phenotyping. However, the 2D-based need extra calibration, or cause destruction to fruit, or can only measure limited and meaningless traits. The 3D-based need extra depth camera, which is expensive and unacceptable for most farmers. In this paper, we propose a non-contact tomato fruit phenotyping method, titled TomatoScanner, where RGB image is all you need for input. First, pixel feature is extracted by instance segmentation of our proposed EdgeYOLO with preprocessing of individual separation and pose correction. Second, depth feature is extracted by depth estimation of Depth Pro. Third, pixel and depth feature are fused to output phenotype results in reality. We establish self-built Tomato Phenotype Dataset to test TomatoScanner, which achieves excellent phenotyping on width, height, vertical area and volume, with median relative error of 5.63%, 7.03%, -0.64% and 37.06%, respectively. We propose and add three innovative modules - EdgeAttention, EdgeLoss and EdgeBoost - into EdgeYOLO, to enhance the segmentation accuracy on edge portion. Precision and mean Edge Error greatly improve from 0.943 and 5.641% to 0.986 and 2.963%, respectively. Meanwhile, EdgeYOLO keeps lightweight and efficient, with 48.7 M weights size and 76.34 FPS. Codes and datasets: https://github.com/AlexTraveling/TomatoScanner.
In this paper, we introduce Latent Bridge Matching (LBM), a new, versatile and scalable method that relies on Bridge Matching in a latent space to achieve fast image-to-image translation. We show that the method can reach state-of-the-art results for various image-to-image tasks using only a single inference step. In addition to its efficiency, we also demonstrate the versatility of the method across different image translation tasks such as object removal, normal and depth estimation, and object relighting. We also derive a conditional framework of LBM and demonstrate its effectiveness by tackling the tasks of controllable image relighting and shadow generation. We provide an open-source implementation of the method at https://github.com/gojasper/LBM.
Accurate depth and camera pose estimation is essential for achieving high-quality 3D visualisations in robotic-assisted surgery. Despite recent advancements in foundation model adaptation to monocular depth estimation of endoscopic scenes via self-supervised learning (SSL), no prior work has explored their use for pose estimation. These methods rely on low rank-based adaptation approaches, which constrain model updates to a low-rank space. We propose Endo-FASt3r, the first monocular SSL depth and pose estimation framework that uses foundation models for both tasks. We extend the Reloc3r relative pose estimation foundation model by designing Reloc3rX, introducing modifications necessary for convergence in SSL. We also present DoMoRA, a novel adaptation technique that enables higher-rank updates and faster convergence. Experiments on the SCARED dataset show that Endo-FASt3r achieves a substantial $10\%$ improvement in pose estimation and a $2\%$ improvement in depth estimation over prior work. Similar performance gains on the Hamlyn and StereoMIS datasets reinforce the generalisability of Endo-FASt3r across different datasets.
Existing camera motion-controlled video generation methods face computational bottlenecks in fine-tuning and inference. This paper proposes LightMotion, a light and tuning-free method for simulating camera motion in video generation. Operating in the latent space, it eliminates additional fine-tuning, inpainting, and depth estimation, making it more streamlined than existing methods. The endeavors of this paper comprise: (i) The latent space permutation operation effectively simulates various camera motions like panning, zooming, and rotation. (ii) The latent space resampling strategy combines background-aware sampling and cross-frame alignment to accurately fill new perspectives while maintaining coherence across frames. (iii) Our in-depth analysis shows that the permutation and resampling cause an SNR shift in latent space, leading to poor-quality generation. To address this, we propose latent space correction, which reintroduces noise during denoising to mitigate SNR shift and enhance video generation quality. Exhaustive experiments show that our LightMotion outperforms existing methods, both quantitatively and qualitatively.
Depth estimation in complex real-world scenarios is a challenging task, especially when relying solely on a single modality such as visible light or thermal infrared (THR) imagery. This paper proposes a novel multimodal depth estimation model, RTFusion, which enhances depth estimation accuracy and robustness by integrating the complementary strengths of RGB and THR data. The RGB modality provides rich texture and color information, while the THR modality captures thermal patterns, ensuring stability under adverse lighting conditions such as extreme illumination. The model incorporates a unique fusion mechanism, EGFusion, consisting of the Mutual Complementary Attention (MCA) module for cross-modal feature alignment and the Edge Saliency Enhancement Module (ESEM) to improve edge detail preservation. Comprehensive experiments on the MS2 and ViViD++ datasets demonstrate that the proposed model consistently produces high-quality depth maps across various challenging environments, including nighttime, rainy, and high-glare conditions. The experimental results highlight the potential of the proposed method in applications requiring reliable depth estimation, such as autonomous driving, robotics, and augmented reality.
Depth ambiguity is a fundamental challenge in spatial scene understanding, especially in transparent scenes where single-depth estimates fail to capture full 3D structure. Existing models, limited to deterministic predictions, overlook real-world multi-layer depth. To address this, we introduce a paradigm shift from single-prediction to multi-hypothesis spatial foundation models. We first present \texttt{MD-3k}, a benchmark exposing depth biases in expert and foundational models through multi-layer spatial relationship labels and new metrics. To resolve depth ambiguity, we propose Laplacian Visual Prompting (LVP), a training-free spectral prompting technique that extracts hidden depth from pre-trained models via Laplacian-transformed RGB inputs. By integrating LVP-inferred depth with standard RGB-based estimates, our approach elicits multi-layer depth without model retraining. Extensive experiments validate the effectiveness of LVP in zero-shot multi-layer depth estimation, unlocking more robust and comprehensive geometry-conditioned visual generation, 3D-grounded spatial reasoning, and temporally consistent video-level depth inference. Our benchmark and code will be available at https://github.com/Xiaohao-Xu/Ambiguity-in-Space.
For scene understanding in unstructured environments, an accurate and uncertainty-aware metric-semantic mapping is required to enable informed action selection by autonomous systems. Existing mapping methods often suffer from overconfident semantic predictions, and sparse and noisy depth sensing, leading to inconsistent map representations. In this paper, we therefore introduce EvidMTL, a multi-task learning framework that uses evidential heads for depth estimation and semantic segmentation, enabling uncertainty-aware inference from monocular RGB images. To enable uncertainty-calibrated evidential multi-task learning, we propose a novel evidential depth loss function that jointly optimizes the belief strength of the depth prediction in conjunction with evidential segmentation loss. Building on this, we present EvidKimera, an uncertainty-aware semantic surface mapping framework, which uses evidential depth and semantics prediction for improved 3D metric-semantic consistency. We train and evaluate EvidMTL on the NYUDepthV2 and assess its zero-shot performance on ScanNetV2, demonstrating superior uncertainty estimation compared to conventional approaches while maintaining comparable depth estimation and semantic segmentation. In zero-shot mapping tests on ScanNetV2, EvidKimera outperforms Kimera in semantic surface mapping accuracy and consistency, highlighting the benefits of uncertainty-aware mapping and underscoring its potential for real-world robotic applications.
The study of security in machine learning mainly focuses on downstream task-specific attacks, where the adversarial example is obtained by optimizing a loss function specific to the downstream task. At the same time, it has become standard practice for machine learning practitioners to adopt publicly available pre-trained vision foundation models, effectively sharing a common backbone architecture across a multitude of applications such as classification, segmentation, depth estimation, retrieval, question-answering and more. The study of attacks on such foundation models and their impact to multiple downstream tasks remains vastly unexplored. This work proposes a general framework that forges task-agnostic adversarial examples by maximally disrupting the feature representation obtained with foundation models. We extensively evaluate the security of the feature representations obtained by popular vision foundation models by measuring the impact of this attack on multiple downstream tasks and its transferability between models.
Semantic perception in driving scenarios plays a crucial role in intelligent transportation systems. However, existing Transformer-based semantic segmentation methods often do not fully exploit their potential in understanding driving scene dynamically. These methods typically lack spatial reasoning, failing to effectively correlate image pixels with their spatial positions, leading to attention drift. To address this issue, we propose a novel architecture, the Hierarchical Spatial Perception Transformer (HSPFormer), which integrates monocular depth estimation and semantic segmentation into a unified framework for the first time. We introduce the Spatial Depth Perception Auxiliary Network (SDPNet), a framework for multiscale feature extraction and multilayer depth map prediction to establish hierarchical spatial coherence. Additionally, we design the Hierarchical Pyramid Transformer Network (HPTNet), which uses depth estimation as learnable position embeddings to form spatially correlated semantic representations and generate global contextual information. Experiments on benchmark datasets such as KITTI-360, Cityscapes, and NYU Depth V2, demonstrate that HSPFormer outperforms several state-of-the-art networks, and achieves promising performance with 66.82% top-1 mIoU on KITTI-360, 83.8% mIoU on Cityscapes, and 57.7% mIoU on NYU Depth V2, respectively. The code will be made publicly available at https://github.com/SY-Ch/HSPFormer.
In the early stages of architectural design, shoebox models are typically used as a simplified representation of building structures but require extensive operations to transform them into detailed designs. Generative artificial intelligence (AI) provides a promising solution to automate this transformation, but ensuring multi-view consistency remains a significant challenge. To solve this issue, we propose a novel three-stage consistent image generation framework using generative AI models to generate architectural designs from shoebox model representations. The proposed method enhances state-of-the-art image generation diffusion models to generate multi-view consistent architectural images. We employ ControlNet as the backbone and optimize it to accommodate multi-view inputs of architectural shoebox models captured from predefined perspectives. To ensure stylistic and structural consistency across multi-view images, we propose an image space loss module that incorporates style loss, structural loss and angle alignment loss. We then use depth estimation method to extract depth maps from the generated multi-view images. Finally, we use the paired data of the architectural images and depth maps as inputs to improve the multi-view consistency via the depth-aware 3D attention module. Experimental results demonstrate that the proposed framework can generate multi-view architectural images with consistent style and structural coherence from shoebox model inputs.
DUSt3R introduced a novel paradigm in geometric computer vision by proposing a model that can provide dense and unconstrained Stereo 3D Reconstruction of arbitrary image collections with no prior information about camera calibration nor viewpoint poses. Under the hood, however, DUSt3R processes image pairs, regressing local 3D reconstructions that need to be aligned in a global coordinate system. The number of pairs, growing quadratically, is an inherent limitation that becomes especially concerning for robust and fast optimization in the case of large image collections. In this paper, we propose an extension of DUSt3R from pairs to multiple views, that addresses all aforementioned concerns. Indeed, we propose a Multi-view Network for Stereo 3D Reconstruction, or MUSt3R, that modifies the DUSt3R architecture by making it symmetric and extending it to directly predict 3D structure for all views in a common coordinate frame. Second, we entail the model with a multi-layer memory mechanism which allows to reduce the computational complexity and to scale the reconstruction to large collections, inferring thousands of 3D pointmaps at high frame-rates with limited added complexity. The framework is designed to perform 3D reconstruction both offline and online, and hence can be seamlessly applied to SfM and visual SLAM scenarios showing state-of-the-art performance on various 3D downstream tasks, including uncalibrated Visual Odometry, relative camera pose, scale and focal estimation, 3D reconstruction and multi-view depth estimation.
Deploying depth estimation networks in the real world requires high-level robustness against various adverse conditions to ensure safe and reliable autonomy. For this purpose, many autonomous vehicles employ multi-modal sensor systems, including an RGB camera, NIR camera, thermal camera, LiDAR, or Radar. They mainly adopt two strategies to use multiple sensors: modality-wise and multi-modal fused inference. The former method is flexible but memory-inefficient, unreliable, and vulnerable. Multi-modal fusion can provide high-level reliability, yet it needs a specialized architecture. In this paper, we propose an effective solution, named align-and-fuse strategy, for the depth estimation from multi-spectral images. In the align stage, we align embedding spaces between multiple spectrum bands to learn shareable representation across multi-spectral images by minimizing contrastive loss of global and spatially aligned local features with geometry cue. After that, in the fuse stage, we train an attachable feature fusion module that can selectively aggregate the multi-spectral features for reliable and robust prediction results. Based on the proposed method, a single-depth network can achieve both spectral-invariant and multi-spectral fused depth estimation while preserving reliability, memory efficiency, and flexibility.