{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mvsplat360-feed-forward-360-scene-synthesis","title":"MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views","arxiv_id":"2411.04924","date":"2024-11-07","proceeding":null,"authors":["Yuedong Chen","Chuanxia Zheng","Haofei Xu","Bohan Zhuang","Andrea Vedaldi","Tat-Jen Cham","Jianfei Cai"],"abstract":"We introduce MVSplat360, a feed-forward approach for 360{\\deg} novel view synthesis (NVS) of diverse real-world scenes, using only sparse observations. This setting is inherently ill-posed due to minimal overlap among input views and insufficient visual information provided, making it challenging for conventional methods to achieve high-quality results. Our MVSplat360 addresses this by effectively combining geometry-aware 3D reconstruction with temporally consistent video generation. Specifically, it refactors a feed-forward 3D Gaussian Splatting (3DGS) model to render features directly into the latent space of a pre-trained Stable Video Diffusion (SVD) model, where these features then act as pose and visual cues to guide the denoising process and produce photorealistic 3D-consistent views. Our model is end-to-end trainable and supports rendering arbitrary views with as few as 5 sparse input views. To evaluate MVSplat360's performance, we introduce a new benchmark using the challenging DL3DV-10K dataset, where MVSplat360 achieves superior visual quality compared to state-of-the-art methods on wide-sweeping or even 360{\\deg} NVS tasks. Experiments on the existing benchmark RealEstate10K also confirm the effectiveness of our model. The video results are available on our project page: https://donydchen.github.io/mvsplat360.","url_abs":"https://arxiv.org/abs/2411.04924v1","url_pdf":"https://arxiv.org/pdf/2411.04924v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mvsplat360-feed-forward-360-scene-synthesis","repo_url":"https://github.com/donydchen/mvsplat360","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"3dgs","task_name":"3DGS"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.04924","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04924"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/donydchen/mvsplat360","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"89c99a8c18402e52","entry":"get_size","repo":"donydchen/mvsplat360","repo_kind":"official","path":"src/scripts/convert_dl3dv.py","file_url":"https://github.com/donydchen/mvsplat360/blob/HEAD/src/scripts/convert_dl3dv.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89c99a8c18402e52"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}