Pith. sign in

REVIEW 20 cited by

ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2310.17994 v2 pith:VPHEIWLR submitted 2023-10-27 cs.CV cs.GR

Kyle Sargent , Zizhang Li , Tanmay Shah , Charles Herrmann , Hong-Xing Yu , Yunzhi Zhang , Eric Ryan Chan , Dmitry Lagun
show 3 more authors
Li Fei-Fei Deqing Sun Jiajun Wu
This is my paper · ORCID
classification cs.CVcs.GR
keywords novelscenesbackgroundsdataproposesynthesisviewzeronvs
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We introduce a 3D-aware diffusion model, ZeroNVS, for single-image novel view synthesis for in-the-wild scenes. While existing methods are designed for single objects with masked backgrounds, we propose new techniques to address challenges introduced by in-the-wild multi-object scenes with complex backgrounds. Specifically, we train a generative prior on a mixture of data sources that capture object-centric, indoor, and outdoor scenes. To address issues from data mixture such as depth-scale ambiguity, we propose a novel camera conditioning parameterization and normalization scheme. Further, we observe that Score Distillation Sampling (SDS) tends to truncate the distribution of complex backgrounds during distillation of 360-degree scenes, and propose "SDS anchoring" to improve the diversity of synthesized novel views. Our model sets a new state-of-the-art result in LPIPS on the DTU dataset in the zero-shot setting, even outperforming methods specifically trained on DTU. We further adapt the challenging Mip-NeRF 360 dataset as a new benchmark for single-image novel view synthesis, and demonstrate strong performance in this setting. Our code and data are at http://kylesargent.github.io/zeronvs/

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 20 Pith papers

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

  1. LSD-3D: Large-Scale 3D Driving Scene Generation with Geometry Grounding

    cs.CV 2025-08 conditional novelty 7.0 of 10

    LSD-3D generates explicit, 3D-consistent driving scenes by combining a generated proxy mesh with geometry-grounded distillation from a 2D diffusion model.

  2. GPS as a Control Signal for Image Generation

    cs.CV 2025-01 conditional novelty 7.0 of 10

    A diffusion model conditioned on GPS tags and text can generate location-specific images and reconstruct 3D landmarks via score distillation sampling, without explicit pose estimation.

  3. Wonderland: Navigating 3D Scenes from a Single Image

    cs.CV 2024-12 conditional novelty 7.0 of 10

    A feed-forward pipeline reconstructs 3D Gaussian scenes from single images by regressing 3DGS directly from camera-conditioned video diffusion latents.

  4. From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos

    cs.CV 2024-12 conditional novelty 7.0 of 10

    A diffusion model trained on 1 million 360-degree videos synthesizes novel views with camera translation and enables 3D reconstruction from a single image.

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

    cs.CV 2026-07 conditional novelty 6.0 of 10

    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.

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

    cs.CV 2026-03 accept novelty 6.0 of 10

    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 of 10

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

  8. CharacterShot: Controllable and Consistent 4D Character Animation

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A new pipeline generates pose-controlled, view-consistent 4D character animations from one reference image and a 2D pose sequence, backed by a new 13,115-character dataset and benchmark.

  9. Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Vid-CamEdit re-synthesizes monocular videos along user-defined camera paths by conditioning a video diffusion model on 2D flows derived from estimated 3D geometry, without training on multi-view video data.

  10. Towards In-the-wild 3D Plane Reconstruction from a Single Image

    cs.CV 2025-06 conditional novelty 6.0 of 10

    ZeroPlane trains a Transformer plane reconstructor on 560K images spanning 10 indoor and outdoor datasets and outperforms prior methods in zero-shot evaluations on NYUv2, 7-Scenes, ParallelDomain, and ApolloScape.

  11. LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fields

    cs.CV 2025-04 conditional novelty 6.0 of 10

    A feed-forward transformer reconstructs shape, PBR materials, and view-dependent radiance from 3 to 6 posed images in under a second, rivaling slower optimization-based inverse rendering.

  12. Pippo: High-Resolution Multi-View Humans from a Single Image

    cs.CV 2025-02 conditional novelty 6.0 of 10

    A single-image multi-view diffusion transformer generates 1K-resolution turnaround views of humans, with attention biasing for many views and a new reprojection-error metric.

  13. Matrix3D: Large Photogrammetry Model All-in-One

    cs.CV 2025-02 conditional novelty 6.0 of 10

    A single multi-modal diffusion transformer trained with masked learning performs pose estimation, depth prediction, and novel view synthesis in one model, reporting SOTA pose and NVS numbers.

  14. UniAvatar: Taming Lifelike Audio-Driven Talking Head Generation with Comprehensive Motion and Lighting Control

    cs.CV 2024-12 conditional novelty 6.0 of 10

    UniAvatar integrates FLAME-based 3D motion rendering and SH-based illumination rendering into a diffusion talking-head model, enabling separate or combined control of motion and lighting in generated videos.

  15. LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors

    cs.CV 2024-12 conditional novelty 6.0 of 10

    LiftImage3D generates small-motion video clips from one image, registers them with MASt3R, and fits a distortion-aware 3D Gaussian field whose canonical scene renders new views.

  16. You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale

    cs.CV 2024-12 reject novelty 6.0 of 10

    See3D proposes a pose-free visual condition for multi-view diffusion trained on web videos, claiming SOTA single- and sparse-view 3D generation, but the evaluation protocol leaks ground-truth information and mixes ben...

  17. Novel View Extrapolation with Video Diffusion Priors

    cs.CV 2024-11 conditional novelty 6.0 of 10

    A training-free video-diffusion refinement stage makes radiance field and point cloud renderings look more realistic when the camera moves far outside the training views.

  18. Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation

    cs.CV 2024-12 conditional novelty 5.0 of 10

    A feed-forward system that generates object-level and scene-level 3D Gaussian scenes from text in about eight seconds by diffusing multi-view RGB-D latent codes and decoding them into pixel-aligned 3D Gaussians.

  19. DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models

    eess.IV 2024-12 conditional novelty 5.0 of 10

    DSplats is a single-stage multiview diffusion model that denoises latents through a 3D Gaussian reconstructor, achieving state-of-the-art single-image-to-3D reconstruction on the Google Scanned Objects benchmark.

  20. Dynamic View Synthesis as an Inverse Problem

    cs.CV 2025-06 reject novelty 3.0 of 10

    Dynamic view synthesis from a monocular video is achieved by redesigning the noise initialization of a pretrained video diffusion model using a recursive interpolation and a stochastic latent modulation.

Pith tools