Pith. sign in

REVIEW 5 cited by

StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis

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 2110.08985 v1 pith:J65OBCJD submitted 2021-10-18 cs.CV stat.ML

Jiatao Gu , Lingjie Liu , Peng Wang , Christian Theobalt This is my paper
classification cs.CVstat.ML
keywords high-resolutionstylenerfconsistencyimageimagescameracontrold-aware
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose StyleNeRF, a 3D-aware generative model for photo-realistic high-resolution image synthesis with high multi-view consistency, which can be trained on unstructured 2D images. Existing approaches either cannot synthesize high-resolution images with fine details or yield noticeable 3D-inconsistent artifacts. In addition, many of them lack control over style attributes and explicit 3D camera poses. StyleNeRF integrates the neural radiance field (NeRF) into a style-based generator to tackle the aforementioned challenges, i.e., improving rendering efficiency and 3D consistency for high-resolution image generation. We perform volume rendering only to produce a low-resolution feature map and progressively apply upsampling in 2D to address the first issue. To mitigate the inconsistencies caused by 2D upsampling, we propose multiple designs, including a better upsampler and a new regularization loss. With these designs, StyleNeRF can synthesize high-resolution images at interactive rates while preserving 3D consistency at high quality. StyleNeRF also enables control of camera poses and different levels of styles, which can generalize to unseen views. It also supports challenging tasks, including zoom-in and-out, style mixing, inversion, and semantic editing.

Discussion (0). Sign in 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. CORGI: Consistency-Aware 3D Dog Reconstruction from a Single Image in the Wild

    cs.CV 2026-07 unverdicted novelty 7.0 of 10

    CORGI reconstructs high-fidelity, animatable 3D dogs from a single in-the-wild image via canonical orbital generation, deformable 3DGS anchored to D-SMAL, and self-supervised generative repair, without 3D supervision.

  2. LaRender: Training-Free Occlusion Control in Image Generation via Latent Rendering

    cs.CV 2025-08 conditional novelty 7.0 of 10

    LaRender replaces cross-attention layers in a pretrained diffusion model with a latent alpha-compositing operation that renders object features in occlusion order, giving training-free occlusion control.

  3. CylinderPlane: Nested Cylinder Representation for 3D-aware Image Generation

    cs.CV 2025-07 conditional novelty 6.0 of 10

    CylinderPlane uses nested cylindrical feature planes instead of Cartesian tri-planes, reducing multi-face artifacts in 360-degree 3D-aware image generation.

  4. SemFaceEdit: Semantic Face Editing on Generative Radiance Manifolds

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A 3D-aware GAN editing method that controls geometry and appearance per semantic region (hair, face, garment, background) using semantic-specific latent codes on radiance manifolds.

  5. EgoAnimate: Generating Human Animations from Egocentric top-down Views

    cs.CV 2025-07 conditional novelty 4.0 of 10

    EgoAnimate synthesizes a frontal T-pose image from an egocentric top-down photo using a fine-tuned Stable Diffusion model, then animates it with off-the-shelf image-to-motion methods to produce an animatable avatar.

Pith tools