3D-Consistent Human Avatars with Sparse Inputs via Gaussian Splatting and Contrastive Learning
- URL: http://arxiv.org/abs/2408.09663v3
- Date: Tue, 19 Nov 2024 12:49:14 GMT
- Title: 3D-Consistent Human Avatars with Sparse Inputs via Gaussian Splatting and Contrastive Learning
- Authors: Haoyu Zhao, Hao Wang, Chen Yang, Wei Shen,
- Abstract summary: CHASE is a novel framework that achieves dense-input-level performance using only sparse inputs.
We introduce a Dynamic Avatar Adjustment (DAA) module, which refines deformed Gaussians by leveraging similar poses from the training set.
While designed for sparse inputs, CHASE surpasses state-of-the-art methods across both full and sparse settings on ZJU-MoCap and H36M datasets.
- Score: 19.763523500564542
- License:
- Abstract: Existing approaches for human avatar generation--both NeRF-based and 3D Gaussian Splatting (3DGS) based--struggle with maintaining 3D consistency and exhibit degraded detail reconstruction, particularly when training with sparse inputs. To address this challenge, we propose CHASE, a novel framework that achieves dense-input-level performance using only sparse inputs through two key innovations: cross-pose intrinsic 3D consistency supervision and 3D geometry contrastive learning. Building upon prior skeleton-driven approaches that combine rigid deformation with non-rigid cloth dynamics, we first establish baseline avatars with fundamental 3D consistency. To enhance 3D consistency under sparse inputs, we introduce a Dynamic Avatar Adjustment (DAA) module, which refines deformed Gaussians by leveraging similar poses from the training set. By minimizing the rendering discrepancy between adjusted Gaussians and reference poses, DAA provides additional supervision for avatar reconstruction. We further maintain global 3D consistency through a novel geometry-aware contrastive learning strategy. While designed for sparse inputs, CHASE surpasses state-of-the-art methods across both full and sparse settings on ZJU-MoCap and H36M datasets, demonstrating that our enhanced 3D consistency leads to superior rendering quality.
Related papers
- TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models [69.0220314849478]
TripoSG is a new paradigm capable of generating high-fidelity 3D meshes with precise correspondence to input images.
The resulting 3D shapes exhibit en- hanced detail due to high-resolution capabilities and demonstrate exceptional fidelity to input im- ages.
To foster progress and innovation in the field of 3D generation, we will make our model publicly available.
arXiv Detail & Related papers (2025-02-10T16:07:54Z) - GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency [50.11520458252128]
Existing 3D affordance learning methods struggle with generalization and robustness due to limited annotated data.
We propose GEAL, a novel framework designed to enhance the generalization and robustness of 3D affordance learning by leveraging large-scale pre-trained 2D models.
GEAL consistently outperforms existing methods across seen and novel object categories, as well as corrupted data.
arXiv Detail & Related papers (2024-12-12T17:59:03Z) - SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting [4.121797302827049]
We propose SelfSplat, a novel 3D Gaussian Splatting model designed to perform pose-free and 3D prior-free generalizable 3D reconstruction from unposed multi-view images.
Our model addresses these challenges by effectively integrating explicit 3D representations with self-supervised depth and pose estimation techniques.
To present the performance of our method, we evaluated it on large-scale real-world datasets, including RealEstate10K, ACID, and DL3DV.
arXiv Detail & Related papers (2024-11-26T08:01:50Z) - Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors [17.544733016978928]
3D object generation from a single image involves estimating the full 3D geometry and texture of unseen views from an unposed RGB image captured in the wild.
Recent advancements in 3D object generation have introduced techniques that reconstruct an object's 3D shape and texture.
We propose bridging the gap between 2D and 3D diffusion models to address this limitation.
arXiv Detail & Related papers (2024-10-12T10:14:11Z) - AugGS: Self-augmented Gaussians with Structural Masks for Sparse-view 3D Reconstruction [9.953394373473621]
Sparse-view 3D reconstruction is a major challenge in computer vision.
We propose a self-augmented two-stage Gaussian splatting framework enhanced with structural masks for sparse-view 3D reconstruction.
Our approach achieves state-of-the-art performance in perceptual quality and multi-view consistency with sparse inputs.
arXiv Detail & Related papers (2024-08-09T03:09:22Z) - GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction [52.04103235260539]
We present a diffusion model approach based on Gaussian Splatting representation for 3D object reconstruction from a single view.
The model learns to generate 3D objects represented by sets of GS ellipsoids.
The final reconstructed objects explicitly come with high-quality 3D structure and texture, and can be efficiently rendered in arbitrary views.
arXiv Detail & Related papers (2024-07-05T03:43:08Z) - GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision [49.839374549646884]
This paper presents GEOcc, a Geometric-Enhanced Occupancy network tailored for vision-only surround-view perception.
Our approach achieves State-Of-The-Art performance on the Occ3D-nuScenes dataset with the least image resolution needed and the most weightless image backbone.
arXiv Detail & Related papers (2024-05-17T07:31:20Z) - JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human
Mesh Recovery [84.67823511418334]
This paper presents 3D JOint contrastive learning with TRansformers framework for handling occluded 3D human mesh recovery.
Our method includes an encoder-decoder transformer architecture to fuse 2D and 3D representations for achieving 2D$&$3D aligned results.
arXiv Detail & Related papers (2023-07-31T02:58:58Z) - Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D
Human Pose Estimation [107.07047303858664]
Large-scale human datasets with 3D ground-truth annotations are difficult to obtain in the wild.
We address this problem by augmenting existing 2D datasets with high-quality 3D pose fits.
The resulting annotations are sufficient to train from scratch 3D pose regressor networks that outperform the current state-of-the-art on in-the-wild benchmarks.
arXiv Detail & Related papers (2020-04-07T20:21:18Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.