DiHuR: Diffusion-Guided Generalizable Human Reconstruction

• URL: http://arxiv.org/abs/2411.11903v1
• Date: Sat, 16 Nov 2024 03:52:23 GMT
• Title: DiHuR: Diffusion-Guided Generalizable Human Reconstruction
• Authors: Jinnan Chen, Chen Li, Gim Hee Lee,
• Abstract summary: We introduce DiHuR, a Diffusion-guided model for generalizable Human 3D Reconstruction and view synthesis from sparse, minimally overlapping images. Our method integrates two key priors in a coherent manner: the prior from generalizable feed-forward models and the 2D diffusion prior, and it requires only multi-view image training, without 3D supervision.
• Score: 51.31232435994026
• License:
• Abstract: We introduce DiHuR, a novel Diffusion-guided model for generalizable Human 3D Reconstruction and view synthesis from sparse, minimally overlapping images. While existing generalizable human radiance fields excel at novel view synthesis, they often struggle with comprehensive 3D reconstruction. Similarly, directly optimizing implicit Signed Distance Function (SDF) fields from sparse-view images typically yields poor results due to limited overlap. To enhance 3D reconstruction quality, we propose using learnable tokens associated with SMPL vertices to aggregate sparse view features and then to guide SDF prediction. These tokens learn a generalizable prior across different identities in training datasets, leveraging the consistent projection of SMPL vertices onto similar semantic areas across various human identities. This consistency enables effective knowledge transfer to unseen identities during inference. Recognizing SMPL's limitations in capturing clothing details, we incorporate a diffusion model as an additional prior to fill in missing information, particularly for complex clothing geometries. Our method integrates two key priors in a coherent manner: the prior from generalizable feed-forward models and the 2D diffusion prior, and it requires only multi-view image training, without 3D supervision. DiHuR demonstrates superior performance in both within-dataset and cross-dataset generalization settings, as validated on THuman, ZJU-MoCap, and HuMMan datasets compared to existing methods.

Related papers

• MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement [23.707586182294932]
  Existing works in single-image human reconstruction suffer from weak generalizability due to insufficient training data or 3D inconsistencies for a lack of comprehensive multi-view knowledge. We introduce MagicMan, a human-specific multi-view diffusion model designed to generate high-quality novel view images from a single reference image.
  arXiv  Detail & Related papers  (2024-08-26T12:10:52Z)
• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)
• GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image [94.56927147492738]
  We introduce GeoWizard, a new generative foundation model designed for estimating geometric attributes from single images. We show that leveraging diffusion priors can markedly improve generalization, detail preservation, and efficiency in resource usage. We propose a simple yet effective strategy to segregate the complex data distribution of various scenes into distinct sub-distributions.
  arXiv  Detail & Related papers  (2024-03-18T17:50:41Z)
• Template-Free Single-View 3D Human Digitalization with Diffusion-Guided LRM [29.13412037370585]
  We present Human-LRM, a diffusion-guided feed-forward model that predicts the implicit field of a human from a single image. Our method is able to capture human without any template prior, e.g., SMPL, and effectively enhance occluded parts with rich and realistic details.
  arXiv  Detail & Related papers  (2024-01-22T18:08:22Z)
• Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstruction [60.52716381465063]
  We introduce Deceptive-NeRF/3DGS to enhance sparse-view reconstruction with only a limited set of input images. Specifically, we propose a deceptive diffusion model turning noisy images rendered from few-view reconstructions into high-quality pseudo-observations. Our system progressively incorporates diffusion-generated pseudo-observations into the training image sets, ultimately densifying the sparse input observations by 5 to 10 times.
  arXiv  Detail & Related papers  (2023-05-24T14:00:32Z)
• Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction [77.69363640021503]
  3D-aware image synthesis encompasses a variety of tasks, such as scene generation and novel view synthesis from images. We present SSDNeRF, a unified approach that employs an expressive diffusion model to learn a generalizable prior of neural radiance fields (NeRF) from multi-view images of diverse objects.
  arXiv  Detail & Related papers  (2023-04-13T17:59:01Z)
• Progressive Multi-view Human Mesh Recovery with Self-Supervision [68.60019434498703]
  Existing solutions typically suffer from poor generalization performance to new settings. We propose a novel simulation-based training pipeline for multi-view human mesh recovery.
  arXiv  Detail & Related papers  (2022-12-10T06:28:29Z)
• NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors [24.05480789681139]
  We propose NeRDi, a single-view NeRF synthesis framework with general image priors from 2D diffusion models. We leverage off-the-shelf vision-language models and introduce a two-section language guidance as conditioning inputs to the diffusion model. We also demonstrate our generalizability in zero-shot NeRF synthesis for in-the-wild images.
  arXiv  Detail & Related papers  (2022-12-06T19:00:07Z)
• Self-supervised Human Mesh Recovery with Cross-Representation Alignment [20.69546341109787]
  Self-supervised human mesh recovery methods have poor generalizability due to limited availability and diversity of 3D-annotated benchmark datasets. We propose cross-representation alignment utilizing the complementary information from the robust but sparse representation (2D keypoints) This adaptive cross-representation alignment explicitly learns from the deviations and captures complementary information: richness from sparse representation and robustness from dense representation.
  arXiv  Detail & Related papers  (2022-09-10T04:47:20Z)

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.