PhysInsert from Beihang and Meitu Achieves Physically Plausible Reference-Based Object Insertion
Yue Gong · hf · 2026-10-30
PhysInsert, from Beihang University, Meitu's MT Lab and Tsinghua, jointly adapts inserted objects and their surrounding scenes for physically plausible reference-based insertion. The team builds the Insert World dataset of strictly aligned Blender-rendered counterfactual pairs with object references across viewpoints and lighting. A Geometry-Guided Adaptation module couples a VGGT geometry stream with image and text streams, while 2D Object-Scene Spatial Supervision jointly supervises object occupancy and environmental changes, grounding spatial instructions in object regions.
More from Multimodal
- Midjourney Style Code sref 3594718371 Produces Striking Metallic Armor Fashion Portraits — sergeantsref · 2026-10-30
- Native 4K with MoSS Image: RoPE NTK vs Upscale Workflows Put to the Test — No-Sleep-4069 · 2026-10-30
- Open-source openjutsu adds 17 relight presets and two-pass Qwen3-VL scene describing — Devajyoti1231 · 2026-10-30
- SpecSlot Boosts Pixel-Space Image Generation: +2.84 FID on ImageNet-512 at Lower Cost — Jiongfan Yang · 2026-10-30
- EveryFrame launches on Bittensor subnet 117: 25 video/image models behind one API from $0.04 per clip — markjeffrey · 2026-10-30
- Pika H3 Flex tested: character swapping and motion transfer with no LoRA needed — linoy_tsaban · 2026-10-30