REVIEW 7 cited by
HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance
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
read the original abstract
The advancements in automatic text-to-3D generation have been remarkable. Most existing methods use pre-trained text-to-image diffusion models to optimize 3D representations like Neural Radiance Fields (NeRFs) via latent-space denoising score matching. Yet, these methods often result in artifacts and inconsistencies across different views due to their suboptimal optimization approaches and limited understanding of 3D geometry. Moreover, the inherent constraints of NeRFs in rendering crisp geometry and stable textures usually lead to a two-stage optimization to attain high-resolution details. This work proposes holistic sampling and smoothing approaches to achieve high-quality text-to-3D generation, all in a single-stage optimization. We compute denoising scores in the text-to-image diffusion model's latent and image spaces. Instead of randomly sampling timesteps (also referred to as noise levels in denoising score matching), we introduce a novel timestep annealing approach that progressively reduces the sampled timestep throughout optimization. To generate high-quality renderings in a single-stage optimization, we propose regularization for the variance of z-coordinates along NeRF rays. To address texture flickering issues in NeRFs, we introduce a kernel smoothing technique that refines importance sampling weights coarse-to-fine, ensuring accurate and thorough sampling in high-density regions. Extensive experiments demonstrate the superiority of our method over previous approaches, enabling the generation of highly detailed and view-consistent 3D assets through a single-stage training process.
Forward citations
Cited by 7 Pith papers
-
3D PixBrush: Image-Guided Local Texture Synthesis
A method that uses a reference image to automatically predict a localization mask and synthesize a matching local texture on a 3D mesh.
-
VideoMat: Extracting PBR Materials from Video Diffusion Models
VideoMat uses a finetuned video diffusion model, intrinsic decomposition, and differentiable path tracing to extract PBR material maps for known 3D geometry from text or image prompts.
-
Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation
Hallo4D uses vision-language models to detect and correct spatial and temporal mistakes in AI-generated 3D and 4D content, improving consistency without retraining the base generators.
-
EarthCrafter: Scalable 3D Earth Generation via Dual-Sparse Latent Diffusion
EarthCrafter generates 600-meter-scale 3D Earth scenes using separate latent diffusion models for structure and texture, conditioned on semantics, images, or nothing.
-
Advancing Text-to-3D Generation with Linearized Lookahead Variational Score Distillation
Updating the LoRA score model one step ahead of the 3D model and keeping only the first-order correction term yields L2-VSD, a stable and higher-quality variant of VSD for text-to-3D generation.
-
XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding
XSpecMesh speeds up auto-regressive mesh generation by about 1.7x using multi-head speculative decoding with cross-attention heads and a probability threshold verification, while keeping output quality close to the ba...
-
DrivingGaussian++: Towards Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes
DrivingGaussian++ reconstructs dynamic surround-view driving scenes and performs training-free multi-task editing (weather, texture, object manipulation) using Gaussians, diffusion models, and LLM-generated trajectories.
Discussion (0). Sign in to comment.