Papers with Code 아카이브
3D Reconstruction
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 7
- 평가표
- 10
- 보존된 평가 기록
- 44
3D Reconstruction is the task of creating a 3D model or representation of an object or scene from 2D images or other data sources. The goal of 3D reconstruction is to create a virtual representation of an object or scene that can be used for a variety of purposes, such as visualization, animation, simulation, and analysis. It can be used in fields such as computer vision, robotics, and virtual reality.
Image: Gwak et al
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/flynn-chen/faceforensics_benchmark
FaceForensics++: Learning to Detect Manipulated Facial Images
https://github.com/flyreelai/sslayout360
SSLayout360: Semi-Supervised Indoor Layout Estimation from 360-Degree Panorama
https://github.com/fuxiao0719/GeoWizard
GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image
https://github.com/fzi-forschungszentrum-informatik/mrf
SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground Truth
https://github.com/garfield-kh/posetriplet
Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognition
https://github.com/gcvcg/voltex
Pixel-Perfect Structure-from-Motion with Featuremetric Refinement
https://github.com/gewanying/shap-anti-spoofing
https://github.com/ghua-ac/end-to-end-synthetic-speech-detection
https://github.com/gmberton/VPR-methods-evaluation
https://github.com/gmberton/auto_vpr
https://github.com/gogojjh/ESVO_extension
https://github.com/gomezzz/geodesynets
Geodesy of irregular small bodies via neural density fields: geodesyNets
https://github.com/goodok/sgnn
SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans
https://github.com/goodproj13/DenserNet
ASLFeat: Learning Local Features of Accurate Shape and Localization
https://github.com/google-research/sparf
Learning Accurate Dense Correspondences and When to Trust Them
https://github.com/guochengqian/magic123
RealFusion: 360° Reconstruction of Any Object from a Single Image
https://github.com/guoxixu/TrafficFlowTracking
MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
https://github.com/haibao637/D2HC-RMVSNet
Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking
https://github.com/hailieqh/3d-object-primitive-graph
https://github.com/happytianhao/tade
Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction
https://github.com/hengyiwang/spann3r
https://github.com/hlinchen/gnesf
NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video
https://github.com/horizontel/aigibench
Generalizable Deepfake Detection via Effective Local-Global Feature Extraction
https://github.com/hrisi/tree-species-classification
https://github.com/hyhchaos/FakePolisher
FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction
https://github.com/hyn2028/llm-cxr
https://github.com/hz-ants/cascade-mvsnet
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
https://github.com/hzlsaber/sida
https://github.com/ibaiGorordo/ONNX-CenterSnap-6D-Pose-and-Shape-Estimation
https://github.com/idiap/eslam
ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields
https://github.com/ishanchadha01/Photometric-Reconstruction-Endoscopy
Photometric single-view dense 3D reconstruction in endoscopy
https://github.com/ishanchadha01/lightneus
LightNeuS: Neural Surface Reconstruction in Endoscopy using Illumination Decline
https://github.com/jasonyzhang/raydiffusion
https://github.com/jazcollins/amazon-berkeley-objects
ABO: Dataset and Benchmarks for Real-World 3D Object Understanding
https://github.com/jhchang/DFDC
FaceForensics++: Learning to Detect Manipulated Facial Images
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.