arXiv Computer Vision By Tim-Felix Faasch, Jochen Kall, Lucas Nunes, Jens Behley, Cyrill Stachniss

TASE: Truncation-Aware Semantic Embeddings for 3D Scene Understanding and Editing

Read the original on arXiv Computer Vision →

TASE introduces a truncation‑aware embedding space that projects pretrained 2D semantic features into 3D scene representations, allowing flexible and controllable editing. The method optimizes feature channels so that fewer channels yield abstract semantics while more channels preserve detail, and it enforces multi‑view consistency with a scale‑ and translation‑equivariant loss. A finetuning stage for the editing diffusion model further reduces artifacts from geometric changes, achieving competitive performance and outperforming prior methods on large‑scale geometric edits.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Computer Vision
2d ago

Chat-Edit-3D++: Interactive 3D and 4D Scene Editing via Large Language Models

The paper introduces Chat-Edit-3D++ (CE3D++), an interactive 3D and 4D scene editing system that uses a Hash-Atlas network to separate 2D editing from 3D reconstruction. CE3D++ employs a large language model to accept arbitrary textual input, interpret user intent, and autonomously invoke appropriate visual models, enabling multi‑round dialogue and diverse editing effects. The approach is extended to monocular 4D scenes by adding motion constraints and a trajectory dataset, allowing a smaller LLM to schedule up to 30 visual tools accurately.

By Shuangkang Fang, Yufeng Wang, Yi-Hsuan Tsai, Wenrui Ding, Yi Yang, Shuchang Zhou, Ming-Hsuan Yang
Hugging Face Trending Papers
Jun 8

EditSSC: Toward Editable Semantic Occupancy Scenes with Unconditional Diffusion Models

3D semantic scene generation is crucial for autonomous driving applications, yet most methods rely on complex 3D-specific architectures such as triplane encoders and adapted diffusion networks, limiting both their simplicity and their editing capabilities. We propose EditSSC, an editing-ready method for 3D semantic scene generation using 2D Bird's Eye View (BEV) representations and off-the-shelf latent diffusion network.

arXiv AI
22h ago

Bernini: Latent Semantic Planning for Video Diffusion

arXiv:2605.22344v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) and diffusion models have each reached remarkable maturity: MLLMs excel at reasoning over heterogene...

By Bernini Team, Chenchen Liu, Junyi Chen, Lei Li, Lu Chi, Mingzhen Sun, Zhuoying Li, Yi Fu, Ruoyu Guo, Yiheng Wu, Ge Bai, Zehuan Yuan