Pith. sign in

REVIEW 22 cited by

ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2408.16767 v4 pith:M6UMHDOJ submitted 2024-08-29 cs.CV cs.AIcs.GR

ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model

classification cs.CV cs.AIcs.GR
keywords scenevideoreconstructionreconxdiffusionmodelsviewscondition
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Advancements in 3D scene reconstruction have transformed 2D images from the real world into 3D models, producing realistic 3D results from hundreds of input photos. Despite great success in dense-view reconstruction scenarios, rendering a detailed scene from insufficient captured views is still an ill-posed optimization problem, often resulting in artifacts and distortions in unseen areas. In this paper, we propose ReconX, a novel 3D scene reconstruction paradigm that reframes the ambiguous reconstruction challenge as a temporal generation task. The key insight is to unleash the strong generative prior of large pre-trained video diffusion models for sparse-view reconstruction. However, 3D view consistency struggles to be accurately preserved in directly generated video frames from pre-trained models. To address this, given limited input views, the proposed ReconX first constructs a global point cloud and encodes it into a contextual space as the 3D structure condition. Guided by the condition, the video diffusion model then synthesizes video frames that are both detail-preserved and exhibit a high degree of 3D consistency, ensuring the coherence of the scene from various perspectives. Finally, we recover the 3D scene from the generated video through a confidence-aware 3D Gaussian Splatting optimization scheme. Extensive experiments on various real-world datasets show the superiority of our ReconX over state-of-the-art methods in terms of quality and generalizability.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 22 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Walking in the Implicit: Interactive World Exploration via Neural Scene Representation

    cs.CV 2026-06 unverdicted novelty 7.0

    NeuWorld uses a transformer VAE to learn compact Neural Implicit Scenes from sparse posed frames and a diffusion transformer to evolve them conditioned on camera trajectories for consistent interactive exploration.

  2. GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction

    cs.CV 2026-05 unverdicted novelty 7.0

    GenRecon lifts object-level generative priors to scene-scale reconstruction by chunking scenes and using projection-based conditioning on multi-view features, claiming 16% better results than prior methods.

  3. Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models

    cs.CV 2026-07 conditional novelty 6.0

    Using a product-of-hyperspheres Riemannian flow matching model on VGGT's latent codes, the authors generate plausible depth, point maps, and RGB for target views from one to four unposed context images.

  4. PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space

    cs.CV 2026-07 conditional novelty 6.0

    A single pixel-space diffusion model jointly performs 3D scene reconstruction and generation by supervising flow matching on rendered multi-view images, matching SOTA reconstruction and outperforming latent-space generation.

  5. Retrieve What's Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation

    cs.CV 2026-06 unverdicted novelty 6.0

    COVRAG improves long-horizon geometric consistency in autoregressive video generation via coverage-maximizing retrieval on lightweight depth-based 3D memory evidence.

  6. LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis

    cs.CV 2026-03 accept novelty 6.0

    Initializing a highway encoder-decoder NVS network from VGGT 3D-aware features yields 31.4 PSNR on RealEstate10k with real-time decoding and optional unposed inputs.

  7. Reevaluating the Intra-Modal Misalignment Hypothesis in CLIP

    cs.CV 2026-03 conditional novelty 6.0

    Diffusing in a unified 3D representation (geometry plus appearance and semantics) produces more cross-view-consistent 3D Gaussian scenes than 2D latent pipelines.

  8. DAV-GSWT: Diffusion-Active-View Sampling for Data-Efficient Gaussian Splatting Wang Tiles

    cs.CV 2026-02 unverdicted novelty 6.0

    DAV-GSWT uses diffusion priors and active view sampling to synthesize high-fidelity Gaussian Splatting Wang Tiles from minimal observations while preserving visual quality and tile transitions.

  9. WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

    cs.CV 2025-12 conditional novelty 6.0

    A real-time video diffusion world model that uses dual action control, reframed position encodings, and context-aligned distillation to keep generated environments consistent over hundreds of frames.

  10. WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

    cs.CV 2025-12 unverdicted novelty 6.0

    WorldPlay uses dual action representation, reconstituted context memory, and context forcing distillation to produce consistent 720p streaming video at 24 FPS for interactive world modeling.

  11. Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models

    cs.CV 2025-11 unverdicted novelty 6.0

    A feed-forward video latent transformer that predicts time-varying 3D Gaussian primitives from one image to produce controllable 4D scenes with appearance, geometry, and motion.

  12. Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations

    cs.RO 2025-07 unverdicted novelty 6.0

    RIGVid shows that filtered AI-generated videos can serve as effective supervision for complex robotic manipulation tasks without any real demonstrations.

  13. PanoImager: Geometry-Guided Novel View Synthesis and Reconstruction from Sparse Panoramic Views

    cs.CV 2026-06 conditional novelty 5.0

    An SfM-free pipeline that turns a few sparse panoramas into a more stable 3D Gaussian map by combining feed-forward pose/depth priors, diffusion view completion, and depth-constrained optimization.

  14. Pantheon360: Taming Digital Twin Generation via 3D-Aware 360{\deg} Video Diffusion

    cs.CV 2026-05 unverdicted novelty 5.0

    Pantheon360 introduces a controllable 360° video diffusion framework that uses an explicit 3D cache from sparse inputs to enforce geometric consistency for digital twin generation.

  15. Generator-Refiner-Examiner: A Tri-Module Data Augmentation Framework for 3D Human Avatar Learning from Monocular Videos

    cs.CV 2026-05 unverdicted novelty 5.0

    TrioMan is a tri-module data augmentation framework using a Generator for pose/camera perturbations, a Refiner with one-step diffusion, and an Examiner with dual-branch attention to improve 3D avatar learning from mon...

  16. Efficient 3D Content Reconstruction and Generation

    cs.CV 2026-05 unverdicted novelty 5.0

    Presents Instant3D for rapid text/image-to-3D generation via multi-view diffusion plus feed-forward reconstruction, and FastMap for 10x faster structure-from-motion with comparable accuracy.

  17. SyncFix: Fixing 3D Reconstructions via Multi-View Synchronization

    cs.CV 2026-04 unverdicted novelty 5.0

    SyncFix improves 3D reconstructions by synchronizing multi-view latent representations in a diffusion refinement process, generalizing from pair-wise training to arbitrary view counts at inference.

  18. Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generation

    cs.CV 2025-12 conditional novelty 5.0

    A diffusion model generates dense 4D point trajectories from a single image, and a separate view-synthesis module renders them into novel-view videos.

  19. VRAG: Learning World Models for Interactive Video Generation

    cs.CV 2025-05 unverdicted novelty 5.0

    The work introduces video retrieval augmented generation (VRAG) with explicit global state conditioning to reduce compounding errors and improve spatiotemporal consistency in interactive video world models.

  20. PanoImager: Geometry-Guided Novel View Synthesis and Reconstruction from Sparse Panoramic Views

    cs.CV 2026-06 unverdicted novelty 4.0

    PanoImager is an SfM-free pipeline combining feed-forward priors, geometry-conditioned diffusion view completion, and depth-guided 3DGS optimization to reconstruct from sparse panoramic images.

  21. DAV-GSWT: Diffusion-Active-View Sampling for Data-Efficient Gaussian Splatting Wang Tiles

    cs.CV 2026-02 reject novelty 4.0

    DAV-GSWT selects views by diffusion-model uncertainty and hallucinates missing structure so Gaussian Splatting Wang Tiles can be made from sparse captures.

  22. Reinforcement Learning: From Algorithms To Foundation Models

    cs.AI 2026-07 conditional novelty 3.0

    A dissertation uniting the author's published results: non-exploitable Nash-DQN policies and the FightLadder benchmark for games, plus diffusion/consistency-model world models for RL — a compilation rather than new results.