{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Daily Paper Cast","title":"BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing","html":"","width":"100%","height":180,"duration":1340,"description":"\n 🤗 Upvotes: 46 | cs.GR, cs.CV\n\n Authors:\n Jiacheng Chen, Ramin Mehran, Xuhui Jia, Saining Xie, Sanghyun Woo\n\n Title:\n BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing\n\n Arxiv:\n http://arxiv.org/abs/2506.17450v2\n\n Abstract:\n We present BlenderFusion, a generative visual compositing framework that synthesizes new scenes by recomposing objects, camera, and background. It follows a layering-editing-compositing pipeline: (i) segmenting and converting visual inputs into editable 3D entities (layering), (ii) editing them in Blender with 3D-grounded control (editing), and (iii) fusing them into a coherent scene using a generative compositor (compositing). Our generative compositor extends a pre-trained diffusion model to process both the original (source) and edited (target) scenes in parallel. It is fine-tuned on video frames with two key training strategies: (i) source masking, enabling flexible modifications like background replacement; (ii) simulated object jittering, facilitating disentangled control over objects and camera. BlenderFusion significantly outperforms prior methods in complex compositional scene editing tasks.\n ","thumbnail_url":"https://img.transistorcdn.com/8lOVNnuwhrA3rxrDMv7Osu4j_t1-jORooO6NfGcQhcw/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS81Zjg1/YzRhODczMDU4MmE4/OGMwN2FiNDlmYzI2/MDliMi5qcGVn.webp","thumbnail_width":300,"thumbnail_height":300}