Pith. sign in

REVIEW 5 cited by

SNeRF: Stylized Neural Implicit Representations for 3D Scenes

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 2207.02363 v1 pith:WYNX6L6L submitted 2022-07-05 cs.CV

Thu Nguyen-Phuoc , Feng Liu , Lei Xiao This is my paper · ORCID
classification cs.CV
keywords novelmethodnerfstylizedscenesstylizationviewviews
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper presents a stylized novel view synthesis method. Applying state-of-the-art stylization methods to novel views frame by frame often causes jittering artifacts due to the lack of cross-view consistency. Therefore, this paper investigates 3D scene stylization that provides a strong inductive bias for consistent novel view synthesis. Specifically, we adopt the emerging neural radiance fields (NeRF) as our choice of 3D scene representation for their capability to render high-quality novel views for a variety of scenes. However, as rendering a novel view from a NeRF requires a large number of samples, training a stylized NeRF requires a large amount of GPU memory that goes beyond an off-the-shelf GPU capacity. We introduce a new training method to address this problem by alternating the NeRF and stylization optimization steps. Such a method enables us to make full use of our hardware memory capacity to both generate images at higher resolution and adopt more expressive image style transfer methods. Our experiments show that our method produces stylized NeRFs for a wide range of content, including indoor, outdoor and dynamic scenes, and synthesizes high-quality novel views with cross-view consistency.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. AGS: Accelerating 3D Gaussian Splatting SLAM via CODEC-Assisted Frame Covisibility Detection

    cs.AR 2025-08 conditional novelty 7.0 of 10

    AGS speeds up 3DGS-SLAM training by measuring frame covisibility from CODEC motion-estimation data, then skipping redundant pose refinements and non-contributory Gaussian computations.

  2. Style4D-Bench: A Benchmark Suite for 4D Stylization

    cs.CV 2025-08 conditional novelty 6.0 of 10

    Style4D-Bench introduces a 12-metric evaluation protocol and a 4DGS-based baseline, Style4D, claimed to achieve state-of-the-art 4D stylization.

  3. Diffusion-Based Attention Warping for Consistent 3D Scene Editing

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A new 3D editing pipeline warps diffusion attention features across views using Gaussian splatting depth, enabling consistent single-view-driven edits.

  4. Incremental Multi-Scene Modeling via Continual Neural Graphics Primitives

    cs.CV 2024-11 conditional novelty 6.0 of 10

    C-NGP incrementally encodes multiple 3D scenes into a single fixed-size Instant-NGP network using pseudo-label conditioning and generative replay, with acceptable quality loss and no access to old training images.

  5. Editing Implicit and Explicit Representations of Radiance Fields: A Survey

    cs.CV 2024-12 conditional novelty 4.0 of 10

    A review that classifies radiance field editing into explicit, latent space, text-guided, compositional, and other categories, with application and dataset tables.

Pith tools