arXiv AI
Jul 2
Interact3D: Compositional 3D Generation of Interactive Objects
arXiv:2603. 16085v2 Announce Type: replace-cross Abstract: Recent breakthroughs in 3D generation have enabled the synthesis of high-fidelity individual assets.
POCI-Diff: 3D-Layout Guided Diffusion for Controllable Synthetic Surveillance Data Generation
Related stories
Hugging Face Trending Papers
Jun 17
LooseControlVideo: Directorial Video Control using Spatial Blocking
Precise 3D spatial orchestration in text-to-video generation remains a significant challenge, particularly for multi-object scenes where semantic layout and temporal dynamics are often entangled. While existing depth-conditioned models achieve good structural fidelity, they necessitate dense, frame-accurate guidance that is labor-intensive to author for dynamic events involving deformable objects.
arXiv Computer Vision
1d ago
CameraEditor: Camera-Controlled Image Editing via Video-Prior Sequential Modeling
arXiv:2609.01479v1 Announce Type: new Abstract: Beyond semantic content, camera parameters play a pivotal role in dictating the geometric perspective and appearance of any given image. While recent i...
arXiv Machine Learning
Jun 9
AccioScene: Compositional 3D Scene Generation via Graph Diffusion and Interaction-driven Critics
arXiv:2502. 06819v2 Announce Type: replace Abstract: This paper presents a framework for generating 3D indoor scenes from text prompts.
arXiv Computer Vision
Aug 27
TASE: Truncation-Aware Semantic Embeddings for 3D Scene Understanding and Editing
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.
arXiv Computer Vision
2d ago
DisCo3D: Distilling Multi-View Consistency for 3D Scene Editing
arXiv:2508.01684v2 Announce Type: replace Abstract: While diffusion models have demonstrated remarkable progress in 2D image generation and editing, extending these capabilities to 3D editing remains...
arXiv AI
23h ago
Bernini: Latent Semantic Planning for Video Diffusion
Bernini proposes a unified framework that separates semantic planning and pixel rendering for video generation and editing. An MLLM-based planner predicts target semantics in ViT embedding space, while a DiT-based renderer synthesizes pixels conditioned on this plan, text features, and source VAE features for editing. The approach introduces Segment-Aware 3D Rotary Positional Embedding and chain-of-thought reasoning, achieving state‑of‑the‑art performance on diverse video benchmarks.
arXiv AI
Aug 6
Place-it-R1: Unlocking Environment-aware Reasoning Potential of MLLM for Video Object Insertion
arXiv:2603. 06140v2 Announce Type: replace-cross Abstract: Video object insertion is fundamental to video editing, yet existing diffusion methods often produce visually plausible but physically inconsistent results.
arXiv AI
Jun 16
SceneConductor: 3D Scene Generation from a Single Image with Multi-Agent Orchestration
arXiv:2606. 08402v2 Announce Type: replace-cross Abstract: Generating complete 3D scenes from a single image requires inferring globally consistent geometry, object relationships, and environmental context from inherently ambiguous visual evidence.
Hugging Face Trending Papers
Jul 21
IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer
Real-world spatial intelligence requires agents to understand scenes from continuous video streams, where objects move, persist, disappear, and reappear over time. While recent spatial foundation models have enabled generalizable feed-forward 3D reconstruction, most streaming methods remain geometry-centric and lack temporally consistent object-level understanding.
arXiv AI
Jun 9
SceneConductor: 3D Scene Generation from Single Image with Multi-Agent Orchestration
arXiv:2606. 08402v1 Announce Type: cross Abstract: Generating complete 3D scenes from a single image requires inferring globally consistent geometry, object relationships, and environmental context from inherently ambiguous visual evidence.
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.