kvuong2711 / WALT3D
Source code for paper WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects under Occlusion (CVPR 2024 Oral)
☆24Updated 5 months ago
Related projects ⓘ
Alternatives and complementary repositories for WALT3D
- [ECCV 2024] Decomposition Betters Tracking Everything Everywhere☆113Updated 4 months ago
- ☆12Updated 2 years ago
- Official implementation of "Physically-Based Lighting for 3D Generative Models of Cars", Computer Graphics Forum 2024 (Proceedings of the…☆17Updated 7 months ago
- ☆35Updated last year
- ☆58Updated last week
- ☆28Updated 9 months ago
- [CVPRW 2023, Best Paper Award] DeFlow: Self-supervised 3D Motion Estimation of Debris Flow☆30Updated last year
- Official PyTorch implementation of Self-Supervised Any-Point Tracking by Contrastive Random Walks, ECCV 2024.☆43Updated 2 weeks ago
- Tame a Wild Camera: In-the-Wild Monocular Camera Calibration☆67Updated 10 months ago
- [BMVC'24] BaseBoostDepth: Exploiting Larger Baselines For Self-supervised Monocular Depth Estimation☆25Updated 3 months ago
- [CVPR 2024] 3DFIRES: Few Image 3D REconstruction for Scenes with Hidden Surfaces☆20Updated 7 months ago
- Few-Image to 3D Method☆69Updated 7 months ago
- Official code for Range-Agnostic Multi-View Depth Estimation with Keyframe Selection (3DV 2024)☆44Updated 9 months ago
- ICCV 2023 Improving Equivariance in State-of-the-Art Supervised Depth and Normal Predictors☆16Updated 4 months ago
- [ECCV 2024] Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions☆74Updated last month
- ConDense backbone, weights, and evaluation code.☆28Updated 4 months ago
- Official implementation of "WorDepth: Variational Language Prior for Monocular Depth Estimation"☆33Updated 2 months ago
- Official Code For Track Everything Everywhere Fast and Robustly☆47Updated 2 months ago
- [CVPR 2024] BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation☆42Updated 6 months ago
- Official PyTorch implementation of "UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Video"☆35Updated 2 months ago
- Scaling Properties of Diffusion Models For Perceptual Tasks☆27Updated last week
- Official implementation of the 2024 ECCV paper SHIC: Shape-Image Correspondences with no Keypoint Annotation☆32Updated last month
- ☆50Updated 2 months ago
- Official implementation of "Local All-Pair Correspondence for Point Tracking" (ECCV 2024)☆136Updated 2 weeks ago
- PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage☆24Updated last month
- [TIV 2024] PyTorch implementation of FlowLens (https://arxiv.org/pdf/2211.11293)☆34Updated 7 months ago
- CVPR 2023 Use NeRF-generated images to train your model.☆74Updated last year
- A large-scale NOCS dataset.☆65Updated 4 months ago
- Implementation of Zero-Shot Video Semantic Segmentation☆35Updated 3 months ago
- ☆84Updated 6 months ago