本合集包含三维重建、点云、场景重建/视图合成/新视角合成等细分任务。
合集下载：点我跳转下载。
1、三维视觉
[1] Learning a 3D Morphable Face Reflectance Model from Low-cost Data
[Code]ReflectanceMM
[2] Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction
[3] LinK: Linear Kernel for LiDAR-based 3D Perception
[Code]https://github.com/MCG-NJU/LinK
2、点云
[1] Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration
[Code]https://github.com/gfmei/UDPReg
[2] Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registration
[Code]https://github.com/qinzheng93/GraphSCNet
[3] Controllable Mesh Generation Through Sparse Latent Point Diffusion Models
[Code]SLIDE: Controllable Mesh Generation Through Sparse Latent Point Diffusion Models
[4] Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis
[Code]https://github.com/ZrrSkywalker/Point-NN
[5] Rotation-Invariant Transformer for Point Cloud Matching
[Code]GitHub - haoyu94/RoITr: Rotation-Invariant Transformer for Point Cloud Matching
[6] GraVoS: Voxel Selection for 3D Point-Cloud Detection
[Code]None
[7] DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets
[Code]https://github.com/Haiyang-W/DSVT
[8] PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees
[Code]None
[9] ACL-SPC: Adaptive Closed-Loop system for Self-Supervised Point Cloud Completion
[Code]https://github.com/Sangminhong/ACL-SPC_PyTorch
[10] DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization
[Code]https://ai4ce.github.io/DeepMapping2/
[11] Frequency-Modulated Point Cloud Rendering with Easy Editing
[12] Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss
[Code]None
[13] ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformer
[Code]GitHub - I2-Multimedia-Lab/ProxyFormer: ProxyFormer (CVPR 2023)
[14] Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting
[Code]https://github.com/tarashakhurana/4d-occ-forecasting
[15] CLIP2: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data
[Code]None
[16] Recognizing Rigid Patterns of Unlabeled Point Clouds by Complete and Continuous Isometry Invariants with no False Negatives and no False Positives
[Code]None
[17] NeuralPCI: Spatio-temporal Neural Field for 3D Point Cloud Multi-frame Non-linear Interpolation
[Code]https://github.com/ispc-lab/NeuralPCI
[18] Unsupervised Inference of Signed Distance Functions from Single Sparse Point Clouds without Learning Priors
[Code]GitHub - chenchao15/NeuralTPS
[19] Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting
[20] Learning Human-to-Robot Handovers from Point Clouds
[Code]Learning Human-to-Robot Handovers from Point Clouds
[21] Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation
[Code]GitHub - hikvision-research/3DVision
[22] PartManip: Learning Cross-Category Generalizable Part Manipulation Policy from Point Cloud Observations
[Code]PartManip
[23] NerVE: Neural Volumetric Edges for Parametric Curve Extraction from Point Cloud
[Code]https://dongdu3.github.io/projects/2023/NerVE/
[24] Self-positioning Point-based Transformer for Point Cloud Understanding
[Code]https://github.com/mlvlab/SPoTr
[25] Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis
[Code]None
[26] MEnsA: Mix-up Ensemble Average for Unsupervised Multi Target Domain Adaptation on 3D Point Clouds
[Code]GitHub - sinAshish/MEnsA_mtda
3、三维重建
[1] PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360°
[Code]PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360°
[2] Transforming Radiance Field with Lipschitz Network for Photorealistic 3D Scene Stylization
[Code]None
[3] TAPS3D: Text-Guided 3D Textured Shape Generation from Pseudo Supervision
[4] MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training
[Code]https://github.com/SmartBot-PJLab/MV-JAR
[5] PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision
[Code]PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision | Konstantinos Tertikas
[6] SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation
[Code]https://yccyenchicheng.github.io/SDFusion/
[7] Masked Wavelet Representation for Compact Neural Radiance Fields
[Code]https://github.com/daniel03c1/masked_wavelet_nerf
[8] Decoupling Human and Camera Motion from Videos in the Wild
[Code]https://vye16.github.io/slahmr/
[9] Structural Multiplane Image: Bridging Neural View Synthesis and 3D Reconstruction
[Code]None
[10] NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction from Multi-view Images
[Code]https://yunfan1202.github.io/NEF/
[11] Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion
[Code]https://github.com/google-research/nerf-from-image
[12] MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices
[Code]http://code.active.vision/MobileBrick/
[13] Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly
[Code]http
[14] NeuDA: Neural Deformable Anchor for High-Fidelity Implicit Surface Reconstruction
[Code]NeuDA
[15] HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling
[Code]https://paulyzheng.github.io/research/hairstep/
[16] MACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervision
[Code]https://imagine.enpc.fr/~guedona/MACARONS/
[17] Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation with Cross-Scale Distortion Awareness
[18] Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapes
[Code]https://jyunlee.github.io/projects/implicit-two-hands/
[19] ECON: Explicit Clothed humans Obtained from Normals
[Code]ECON: Explicit Clothed humans Optimized via Normal integration
[20] Structured 3D Features for Reconstructing Relightable and Animatable Avatars
[Code]https://enriccorona.github.io/s3f/
[21] Structured 3D Features for Reconstructing Controllable Avatars
[Code]None
[22] BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects
[Code]BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects
[23] Seeing Through the Glass: Neural 3D Reconstruction of Object Inside a Transparent Container
[Code]GitHub - hirotong/ReNeuS
[24] HexPlane: A Fast Representation for Dynamic Scenes
[Code]HexPlane
[25] PAniC-3D: Stylized Single-view 3D Reconstruction from Portraits of Anime Characters
[26] 3D Line Mapping Revisited
[Code]GitHub - cvg/limap: A toolbox for mapping and localization with line features.
[27] Multi-View Azimuth Stereo via Tangent Space Consistency
[Code]https://github.com/xucao-42/mvas
4、场景重建/视图合成/新视角合成
[1] SINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing Field
[Code]https://zju3dv.github.io/sine/
[2] ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision
[3] Balanced Spherical Grid for Egocentric View Synthesis
[Code]EgoNeRF - Changwoon Choi
[4] Robust Dynamic Radiance Fields
[Code]RoDynRF: Robust Dynamic Radiance Fields
[5] Semantic Ray: Learning a Generalizable Semantic Field with Cross-Reprojection Attention
[Code]https://liuff19.github.io/S-Ray/
[6] MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures
[Code]MobileNeRF
[7] I2-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs
[Code]https://jingsenzhu.github.io/i2-sdf/
[8] Learning Detailed Radiance Manifolds for High-Fidelity and 3D-Consistent Portrait Synthesis from Monocular Image
[Code]https://yudeng.github.io/GRAMInverter/
[9] Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation from 2D Supervision
[Code]https://jetd1.github.io/nerflets-web/
[10] Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields
[Code]https://rover-xingyu.github.io/L2G-NeRF/
[11] DP-NeRF: Deblurred Neural Radiance Field with Physical Scene Priors
[Code]https://dogyoonlee.github.io/dpnerf/
[12] SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fields
[Code]SPIn-NeRF
[13] 3D Video Loops from Asynchronous Input
[Code]https://limacv.github.io/VideoLoop3D_web/
[14] NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer
[Code]https://redrock303.github.io/nerflix/
[15] NeRF-Gaze: A Head-Eye Redirection Parametric Model for Gaze Estimation
[Code]None
[16] Renderable Neural Radiance Map for Visual Navigation
[Code]https://rllab-snu.github.io/projects/RNR-Map/
[17] Real-Time Neural Light Field on Mobile Devices
[Code]https://snap-research.github.io/MobileR2L/
[18] Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures
[19] NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior
[Code]Nope-NeRF
[20] SPARF: Neural Radiance Fields from Sparse and Noisy Poses
[Code]https://prunetruong.com/sparf.github.io/
[21] EventNeRF: Neural Radiance Fields from a Single Colour Event Camera
[Code]EventNeRF: Neural Radiance Fields from a Single Colour Event Camera
[22] Grid-guided Neural Radiance Fields for Large Urban Scenes
[Code]https://city-super.github.io/gridnerf/
[23] HandNeRF: Neural Radiance Fields for Animatable Interacting Hands
[Code]None
[24] ABLE-NeRF: Attention-Based Rendering with Learnable Embeddings for Neural Radiance Field
[Code]None
[25] Progressively Optimized Local Radiance Fields for Robust View Synthesis
[Code]Progressively Optimized Local Radiance Fields for Robust View Synthesis
[26] GM-NeRF: Learning Generalizable Model-based Neural Radiance Fields from Multi-view Images
[Code]GitHub - JanaldoChen/GM-NeRF
[27] MAIR: Multi-view Attention Inverse Rendering with 3D Spatially-Varying Lighting Estimation
[Code]None
[28] Interactive Segmentation of Radiance Fields
[Code]https://rahul-goel.github.io/isrf/
[29] Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization
[Code]Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields
[30] DiffRF: Rendering-Guided 3D Radiance Field Diffusion
[Code]https://sirwyver.github.io/DiffRF/
[31] Magic3D: High-Resolution Text-to-3D Content Creation
[Code]Magic3D: High-Resolution Text-to-3D Content Creation
[32] JAWS: Just A Wild Shot for Cinematic Transfer in Neural Radiance Fields
[Code]JAWS
[33] SUDS: Scalable Urban Dynamic Scenes
[Code]https://haithemturki.com/suds/
[34] NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects
[35] FlexNeRF: Photorealistic Free-viewpoint Rendering of Moving Humans from Sparse Views
[Code]FlexNeRF: Photorealistic Free-viewpoint Rendering of Moving Humans from Sparse Views
[36] DyLiN: Making Light Field Networks Dynamic
[Code]DyLiN: Making Light Field Networks Dynamic
[37] Efficient View Synthesis and 3D-based Multi-Frame Denoising with Multiplane Feature Representations
[Code]None
[38] NeRF-Supervised Deep Stereo
[Code]NeRF-Supervised Deep Stereo
[39] Consistent View Synthesis with Pose-Guided Diffusion Models
[Code]Consistent View Synthesis with Pose-Guided Diffusion Models
[40] Enhanced Stable View Synthesis
[Code]None
[41] NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illumination
[Code]None
[42] F²-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories
[Code]F2-NeRF
[43] Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenes
[Code]https://nv-tlabs.github.io/fegr/
[44] GINA-3D: Learning to Generate Implicit Neural Assets in the Wild
[Code]None
[45] MonoHuman: Animatable Human Neural Field from Monocular Video
[Code]MonoHuman: Animatable Human Neural Field from Monocular Video
[46] One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Field
[Code]https://www.waytron.net/hidenerf/
[47] Neural Lens Modeling
[Code]NeuralLens
[48] Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos
[Code]None
[49] POEM: Reconstructing Hand in a Point Embedded Multi-view Stereo
[Code]GitHub - lixiny/POEM: [CVPR 2023] POEM: Reconstructing Hand in a Point Embedded Multi-view Stereo
[50] Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field