paper-with-me

Papers 3D Generation

“3D Generation” 태그가 달린 논문 629편 · 필터 해제

SNAP3D: Physically Grounded 3D Parts for Assembly from a Single Image

2026-09-11 · Yu-Rou Tuan, Hao-Tang Tsui, Nicolas Ugrinovic, Kris Kitani 외 hf

Part-aware 3D asset generation enables applications such as editing, articulation, simulation, and fabrication, yet existing methods can generate visually complete individual parts without ensuring that they form a valid…

3D Generation

Guiding Image-to-3D Generation with Test-Time Partial Observations

2026-09-09 · Jerred Chen, Simon Weber, Ronald Clark arxiv

Image-to-3D models can generate visually compelling 3D assets from a single RGB image, but their geometry is often only loosely constrained by the available observations, limiting their use in applications that require g…

3D Generation

ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes

2026-09-01 · Mingda Lin, Weijie Wang, Zeyu Zhang, Bowen Cui 외 hf

Compact token sequences are essential for efficient 3D generation. However, existing 3D tokenizers typically organize latent representations either over spatial regions or as fixed-size sets of global tokens, both suffer…

3D Generation

Cyc3D: Evaluating Cyclic Structural Stability and Asset Usability in Image-to-3D Generation

2026-08-28 · Liwen Zhang arxiv

Image-conditioned 3D generation has advanced rapidly, yet existing evaluation protocols largely judge rendered-view plausibility and semantic alignment, overlooking whether a generator forms a stable 3D interpretation an…

3D Generation

Luce: Relightable Gaussians for 3D Asset Generation

2026-08-25 · Mayank Singh, Michele Stoppa, Alvise Memo, Rui Yu 외 hf

High-fidelity image-to-3D generation requires a 3D representation that captures both geometry and appearance. To support relighting and integration into standard rendering pipelines, the representation should include phy…

3D Generation

Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion

2026-08-20 · Bowen Cui, Weijie Wang, Zeyu Zhang, Yefei He 외 arxiv

While text-to-3D generation has advanced rapidly, achieving high geometric fidelity at low inference cost remains challenging. Existing text-to-3D methods either decode discrete shape tokens autoregressively or iterative…

3D Generation

SemanticSlider3D: Training-Free Continuous Semantic Editing for 3D Objects

2026-08-19 · Ru Wang, Rahul Jain, Koichiro Niinuma, Aakar Gupta arxiv

Fine-grained control over continuous semantic attributes of 3D objects is essential for 3D content creation, but is not well supported by conventional 3D modeling workflows or prompt-based interaction with existing gener…

Image Generation3D Generation

MegaParts: Scaling Part-Aware 3D Object Generation to 300 Parts via Token-Efficient Autoregressive Modeling

2026-08-14 · Manwen Liao, Xinyu Lian, Jian Mao, Kaixu Chen 외 hf

Part-aware 3D object generation is essential for graphics applications such as controllable modeling, editing, and articulation, where objects are represented as coherent assemblies of semantic parts. However, existing p…

3D Generation

SCULPT: Subtractive Composition for 3D Part Generation

2026-08-13 · Sikuang Li, Chen Yang, Jiemin Fang, Jiazhong Cen 외 arxiv

Part-aware 3D generation aims to create digital assets that are coherent as complete objects while exposing structural parts for editing, material assignment, animation, and reuse. Existing methods impose this structure …

3D Generation

PixSDS: Why Latent SDS Makes Noisy Pixels

2026-08-13 · Vsevolod Skorokhodov arxiv

Score Distillation Sampling (SDS) enables text-to-3D generation by optimizing rendered images with a pretrained diffusion prior, but latent SDS often produces structured color artifacts and high-frequency texture noise. …

3D Generation

To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation

2026-08-06 · Xiaobin Huang, Zilong Huang, Yang Luo, Hongchao Fan 외 arxiv

Text-driven 3D generation has advanced rapidly in creating large-scale outdoor environments and detailed indoor scenes, but these domains are usually synthesized independently, lacking the correspondence required for a c…

3D Generation

Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing

2026-08-03 · Junliang Ye, Kenkun Liu, Guocun Wang, Yang Li 외 hf

Recent advances in image generation have demonstrated the potential of unified multimodal models that integrate understanding, generation, and editing. However, unified 3D modeling remains constrained by scarce multimoda…

Image Generation3D Generation

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation

2026-07-30 · Xiao Luo, Mingyang Du, Xin Zhou, Tianrui Feng 외 arxiv

High-fidelity 3D generation predominantly relies on scaling model capacity and data, which incurs prohibitive computational costs. This paradigm typically requires learning geometry from scratch and overlooks the rich se…

3D Generation

DiffGI: Differentiable Geometry Images for High-Fidelity Thin-Shell 3D Generation

2026-07-15 · Eungjune Shim, Hansol Lee, Eunjung Ju hf

Existing 3D generative models predominantly rely on implicit volumetric representations, which enforce watertight topology and struggle to represent thin-shell and non-manifold geometries such as garments. Geometry image…

3D Generation

Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation

2026-07-14 · Hongbo Wang, Huaibo Huang, Jie Cao, Jin Liu 외 arxiv

While recent advances in 3D generation have enabled impressive visual synthesis, existing methods often rely on 2D diffusion supervision without explicit mechanisms for geometric consistency, leading to spatial hallucina…

3D Generation

3D-DefectBench: A Controlled Factorial Study of Vision-Language Model Evaluation Pipelines for Fine-Grained 3D Generation Defects

2026-07-12 · Zhenyu Zhao, Nanshan Jia, Jihyeon Je, Yifu Tang 외 arxiv

Automated evaluation is essential for scaling generative 3D systems, where exhaustive human review is costly and slow. However, the reliability of an automated judge depends on the entire evaluation pipeline, not only th…

3D Generation

ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation

2026-07-07 · Tianjiao Yu, Xinzhuo Li, Yifan Shen, Onkar Susladkar 외 arxiv

Unified 3D foundation models aspire to generate 3D assets and reason about them in language within a single backbone, but their text-3D interaction remains largely implicit. Existing methods concatenate text and 3D token…

3D Generation

CoGen3D: An Agentic Human-AI Co-Design Pipeline for 3D Asset Generation for Virtual Reality

2026-07-04 · Weiwei Jiang, Wanyu He, Zheyu Tan, Zheyuan Kuang 외 arxiv

Creating 3D assets for virtual reality requires modeling expertise, which restricts the authorship of immersive experiences. Existing generative AI tools rely on unconstrained, command-driven prompting, lacking the conve…

3D Generation

InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360° Image

2026-07-04 · Gwanhyeong Koo, Hyunsu Kim, Youngji Kim, Taejae Lee 외 arxiv

Recent advances in single image-to-3D generation have enabled high-quality asset synthesis, yet extending these capabilities to indoor scene generation remains challenging. Existing methods focus on asset-level generatio…

Scene Generation3D Generation

Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models

2026-07-01 · Yue Han, Chong Li, Zhening Liu, Cong Huang 외 arxiv

Recent 3D generative models can synthesize high-quality geometry but often struggle to reproduce intricate textures from reference images, largely due to the scarcity of large-scale 3D training data with rich surface app…

Video Generation3D Generation
1–20 / 629 다음 →