🔥 Paper Reading List (2024)

Paper Reading List in 2024 (Work-in-Progress)

  1. S-VolSDF: Sparse Multi-View Stereo Regularization of Neural Implicit Surfaces
    Link to Paper

  2. GenS: Generalizable Neural Surface Reconstruction from Multi-View Images
    Link to Paper

  3. Digging into Uncertainty in Self-supervised Multi-view Stereo
    Link to Paper

  4. NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo
    Link to Paper

  5. Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation
    Link to Paper

  6. Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume
    Link to Paper

  7. Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields, ICCV 2023
    Link to Paper

  8. Instant-NGP: Instant Neural Graphics Primitives with a Multiresolution Hash Encoding, SIGGRAPH 2022
    Link to Paper

  9. Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields, ICCV 2021
    Link to Paper

  10. Mip-nerf 360: Unbounded anti-aliased neural radiance fields, CVPR 2022
    Link to Paper

  11. GMFlow: Learning Optical Flow via Global Matching, CVPR 2022
    Link to Paper

  12. Iterative geometry encoding volume for stereo matching, CVPR 2023
    Link to Paper

  13. Parameterized Cost Volume for Stereo Matching, ICCV 2023
    Link to Paper

  14. High-frequency Stereo Matching Network, CVPR 2023
    Link to Paper

  15. Digging into uncertainty-based pseudo-label for robust stereo matching, TPAMI 2023
    Link to Paper

  16. Masked representation learning for domain generalized stereo matching, CVPR 2023
    Link to Paper

  17. Learning Depth Estimation for Transparent and Mirror Surfaces, ICCV 2023
    Link to Paper

  18. Efficient Multi-view Stereo by Iterative Dynamic Cost Volume, CVPR 2022
    Link to Paper

  19. MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions, CVPR 2022
    Link to Paper

  20. (DLNR) High-frequency stereo matching network, CVPR 2023
    Link to Paper

  21. (ACVNet) Attention Concatenation Volume for Accurate and Efficient Stereo Matching, CVPR 2022
    Link to Paper

  22. Learning in the Frequency Domain, CVPR 2020
    Link to Paper

  23. Fast Vision Transformers with HiLo Attention, NeurIPS 2022
    Link to Paper

  24. On the Over-Smoothing Problem of CNN Based Disparity Estimation, ICCV 2019
    Link to Paper

  25. (PDSNet) Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching, NeruIPS 2018
    Link to Paper

  26. (NP-CVP-MVSNet) Non-parametric depth distribution modeling based depth inference for multi-view stereo, CVPR 2022
    Link to Paper

  27. Itsa: An information-theoretic approach to automatic shortcut avoidance and domain generalization in stereo matching networks, CVPR 2022
    Link to Paper

  28. GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Feature, CVPR 2022
    Link to Paper

  29. Extreme Rotation Estimation using Dense Correlation Volumes, CVPR 2021
    Link to Paper

  30. The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs, 3DV 2022
    Link to Paper

  31. DynamicStereo: Consistent Dynamic Depth from Stereo Videos, CVPR 2023
    Link to Paper

  32. Deep Depth Completion of a Single RGB-D Image, CVPR 2018
    Link to Paper

  33. CompletionFormer: Depth Completion with Convolutions and Vision Transformers, CVPR 2023
    Link to Paper

  34. Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints, ICCV 2019
    Link to Paper

  35. Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image, ICRA 2018
    Link to Paper

  36. LiStereo: Generate Dense Depth Maps from LIDAR and Stereo Imagery, ICRA 2020
    Link to Paper

  37. High-precision Depth Estimation with the 3D LiDAR and Stereo Fusion, ICRA 2018
    Link to Paper

  38. Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data, ArXiv
    Link to Paper

  39. Mosaic-SDF for 3D Generative Models, ArXiv
    Link to Paper

  40. SparsePose: Sparse-View Camera Pose Regression and Refinement, CVPR 2023
    Link to Paper

  41. FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation, CVPR 2023
    Link to Paper

  42. Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning, CVPR 2021
    Link to Paper

  43. DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling, CVPR 2023
    Link to Paper

  44. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results, NeurIPS 2018
    Link to Paper

  45. (Flow-Supervisor) Semi-Supervised Learning of Optical Flow by Flow Supervisor, ECCV 2022
    Link to Paper

  46. ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth, ArXiv 2023
    Link to Paper

  47. GraftNet: Towards Domain Generalized Stereo Matching With a Broad-Spectrum and Task-Oriented Feature, CVPR 2022
    Link to Paper

  48. (CoodConv) An intriguing failing of convolutional neural networks and the CoordConv solution, NeurIPS 2018
    Link to Paper

  49. (CODD) Temporally Consistent Online Depth Estimation in Dynamic Scenes, WACV 2023
    Link to Paper

  50. SPECTRAL NORMALIZATION FOR GENERATIVE ADVERSARIAL NETWORKS, ICLR 2018
    Link to Paper

  51. NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction, NeurIPS 2021
    Link to Paper

  52. (Semantic-NeRF) In-Place Scene Labelling and Understanding with Implicit Scene Representation, ICCV 2021, Oral
    Link to Paper

  53. VR-GS: A Physical Dynamics-Aware Interactive Gaussian Splatting System in Virtual Reality, ArXiv 2024
    Link to Paper

  54. Gaussian Splatting SLAM, CVPR 2024
    Link to Paper

  55. From Coarse to Fine: Robust Hierarchical Localization at Large Scale, CVPR 2019
    Link to Paper

  56. VINDLU: A Recipe for Effective Video-and-Language Pretraining, CVPR 2023
    Link to Paper

  57. Tag2Text: Guiding Vision-Language Model via Image Tagging, ICLR 2024
    Link to Paper

  58. (RAM) Recognize Anything: A Strong Image Tagging Model, CVPR Workshop 2024
    Link to Paper

  59. pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction, CVPR 24, Oral
    Link to Paper

  60. Unifying Flow, Stereo and Depth Estimation, TPAMI 2023
    Link to Paper

  61. Language-Assisted 3D Feature Learning for Semantic Scene Understanding, AAAI 2023
    Link to Paper

  62. (Good Blog) - What are Diffusion Models?
    Link to Blog

  63. (latent-diffusion) High-Resolution Image Synthesis with Latent Diffusion Models, CVPR 2022
    Link to Paper

  64. ELFNet: Evidential Local-global Fusion for Stereo Matching (ICCV 2023)
    Link to Paper

  65. Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers, ICCV 2021 Oral
    Link to Paper
    Check its Github repo for good attention visualization.

  66. Low-rank bottleneck in multi-head attention models, PMLR 2020
    Link to Paper

  67. High-frequency Stereo Matching Network, CVPR 2023
    Link to Paper

  68. Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching, CVPR 2024
    Link to Paper

  69. MoCha-Stereo: Motif Channel Attention Network for Stereo Matching, CVPR 2024
    Link to Paper

  70. COTRACKER3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos
    Link to Paper

  71. Understanding Masked Image Modeling via Learning Occlusion Invariant Feature, CVPR 2023
    Link to Paper

  72. Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions, ECCV 2024
    Link to Paper

  73. 3D VISION-LANGUAGE GAUSSIAN SPLATTING
    Link to Paper

  74. 3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt
    Link to Paper

  75. Towards Foundation Models for 3D Vision: How Close Are We?
    Link to Paper

  76. FlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models, CVPR 2024
    Link to Paper

  77. (OSEDiff) One-Step Effective Diffusion Network for Real-World Image Super-Resolution, NeurIPS 2024
    Link to Paper, Link to Code

  78. DiffRAW: Leveraging Diffusion Model to Generate DSLR-Comparable Perceptual Quality sRGB from Smartphone RAW Images, AAAI 2024
    Link to Paper N/A

  79. Patch-level Representation Learning for Self-supervised Vision Transformers, CVPR 2022
    Link to Paper

  80. Self-Supervised Representation Learning from Flow Equivariance, ICCV 2021
    Link to Paper

  81. 3D Common Corruptions and Data Augmentation, CVPR 2022, Oral
    Link to Paper

  82. NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video, CVPR 2021, Oral
    Link to Paper

  83. Passthrough+: Real-time Stereoscopic View Synthesis for Mobile Mixed Reality, Proceedings of the ACM on Computer Graphics and Interactive Techniques, 2020
    Link to Paper

  84. Crafting Better Contrastive Views for Siamese Representation Learning, CVPR 2022, Oral
    Link to Paper

  85. Masked Autoencoders Are Scalable Vision Learners
    Link to Paper

  86. How to Understand Masked Autoencoders
    Link to Paper

  87. Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation, CVPR 2022
    Link to Paper

  88. Deep Homography for Efficient Stereo Image Compression, CVPR 2021
    Link to Paper

  89. Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers, ICCV 2021
    Link to Paper

  90. DeepMVS: Learning Multi-View Stereopsis, CVPR 2018
    Link to Paper

  91. Neural RGB->D Sensing: Depth and Uncertainty from a Video Camera, CVPR 2019
    Link to Paper

  92. Depth Map Prediction from a Single Image using a Multi-Scale Deep Network, NeurIPS 2014
    Link to Paper

  93. View-Consistent 3D Editing with Gaussian Splatting, ECCV 2024
    Link to Paper

  94. Text2Scene: Text-Driven Indoor Scene Stylization with Part-Aware Details, CVPR 2023
    Link to Paper

  95. Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts, ECCV 2024
    Link to Paper

  96. HDRSplat: Gaussian Splatting for High Dynamic Range 3D Scene Reconstruction, BMVC 2024
    Link to Paper

  97. pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction, CVPR 2024 Oral
    Link to Paper

  98. DepthSplat: Connecting Gaussian Splatting and Depth, arXiv 2024
    Link to Paper

  99. SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM, CVPR 2024
    Link to Paper
Written on November 13, 2024