Paper Detail

4D Human-Scene Reconstruction from Low-Overlap Captures

Minhyuk Hwang, Sangmin Kim, Seunguk Do, Daneul Kim, Jaesik Park

huggingface Score 5.0

Published 2026-07-10 · First seen 2026-07-14

General AI

Abstract

Existing volumetric capture of dynamic human performance achieves high fidelity with dense camera arrays. However, in real-world scenarios, only a handful of low-overlap cameras are available, which degrades the output quality and leaves large areas unobserved. Recent 4D reconstruction methods have focused on low-overlap settings, yet they still produce noticeable artifacts in under-observed regions. Video diffusion models have emerged as another option, but they show geometrically inconsistent results for humans. To address these limitations, we propose StudioRecon, a pipeline that reconstructs 4D human scenes from sparse, low-overlap cameras by decoupling background and humans. We densify background supervision by synthesizing hundreds of camera-controlled novel views with a video diffusion model. We also robustly initialize deformable Gaussian humans with cross-view identity association and triangulated multi-view keypoint fitting. Finally, our recursive enhancement module with motion-adaptive consistency injection harmonizes the composed output, thereby further avoiding remaining artifacts. We achieve state-of-the-art novel view synthesis across four real-world datasets and demonstrate applications such as novel trajectory rendering and human replacement.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{hwang20264d,
  title = {4D Human-Scene Reconstruction from Low-Overlap Captures},
  author = {Minhyuk Hwang and Sangmin Kim and Seunguk Do and Daneul Kim and Jaesik Park},
  year = {2026},
  abstract = {Existing volumetric capture of dynamic human performance achieves high fidelity with dense camera arrays. However, in real-world scenarios, only a handful of low-overlap cameras are available, which degrades the output quality and leaves large areas unobserved. Recent 4D reconstruction methods have focused on low-overlap settings, yet they still produce noticeable artifacts in under-observed regions. Video diffusion models have emerged as another option, but they show geometrically inconsistent },
  url = {https://huggingface.co/papers/2607.09125},
  keywords = {huggingface daily},
  eprint = {2607.09125},
  archiveprefix = {arXiv},
}

Metadata

{}