Newest papers

Gate3DGen: A Pre-processing Model that Selectively Purifies Real-World Images for 3D Generation

Xiaolin Li, Zihao Huang, Fanpeng Meng, Chen Yang, Guanjun Wu, Kai Zhang, Jiemin Fang, Qi Tian · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31649 · cited by 0 works (OpenAlex) · open-access PDF

Arabic

وقد حصلت إصدارات 3D الذكية على مستوى عال من الإثباتات على النتائج المحددة، لكنها تدهور بشكل كبير على الصور في العالم الحقيقي مع الإضاءة غير المحددة، والغثيان، والغثيانات. تحرير مثل هذه الإصدارات يتطلب تحديد موعد الإضراب وتخزين الإشارات البصرية اللازمة لإنتاج 3D، في حين تترك الإشارات النظيفة دون تغيير. ونحن نقدم Gate3DGen، نموذجًا إبداعيًا متكاملًا يهدف إلى معالجة البيانات المحددة إلى الإصدارات 3D الحالية دون إعادة تدريبها. يُنظر إلى أن راديوهات الذكية التي تعاني من الإثباتات تترك الإشارات المحددة التي تم تصنيفها كأنها

Machine translation (Meta M2M100); the English original follows.

Abstract

Single-image 3D generation has achieved high fidelity on curated benchmarks, yet degrades sharply on real-world images with uneven illumination, blur, and occlusions. Purifying such inputs requires deciding when to intervene and preserving the visual cues needed for 3D generation, while leaving clean inputs unchanged. We introduce Gate3DGen, a selective pre-processing model that gates image inputs to existing 3D generators without retraining them. A degradation-aware router bypasses inputs classified as clean and extracts features to guide purification of the remaining inputs. Conditioned on these features, a 3D-oriented one-step purifier purifies degraded inputs with spatial losses that encourage preservation of object identity, contours, and textural cues. To provide paired supervision, we construct a synthetic data engine that renders clean views of 3D assets and synthesises composite degradations. On the synthetic benchmark, the purifier improves image fidelity and downstream 3D geometry in only 2.3s on average, reducing TRELLIS.2 mesh distance by 61.5% relative to degraded inputs. VLM evaluation and human preferences on real photographs further support identity preservation and degradation correction. More demos and code are available at https://supra-3d.github.io/gate3dgen.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Object (grammar), Computer science, Artificial intelligence, Engineering, Computer vision, Fidelity

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31649, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange