{"type":"ScholarlyArticle","title":"Hybrid Mesh-Gaussian Representation for Efficient Indoor Scene Reconstruction","authors":[{"name":"Binxiao Huang","slug":"binxiao-huang","given":"Binxiao","family":"Huang","affiliation":""},{"name":"Zhihao Li","slug":"zhihao-li","given":"Zhihao","family":"Li","affiliation":""},{"name":"Shiyong Liu","slug":"shiyong-liu","given":"Shiyong","family":"Liu","affiliation":""},{"name":"Xiao Tang","slug":"xiao-tang","given":"Xiao","family":"Tang","affiliation":""},{"name":"Jiajun Tang","slug":"jiajun-tang","given":"Jiajun","family":"Tang","affiliation":""},{"name":"Jiaqi Lin","slug":"jiaqi-lin","given":"Jiaqi","family":"Lin","affiliation":""},{"name":"Yuxin Cheng","slug":"yuxin-cheng","given":"Yuxin","family":"Cheng","affiliation":""},{"name":"Zhenyu Chen","slug":"zhenyu-chen","given":"Zhenyu","family":"Chen","affiliation":""},{"name":"Xiaofei Wu","slug":"xiaofei-wu","given":"Xiaofei","family":"Wu","affiliation":""},{"name":"Ngai Wong","slug":"ngai-wong","given":"Ngai","family":"Wong","affiliation":""}],"abstract":"3D Gaussian splatting (3DGS) has demonstrated exceptional performance in image-based 3D reconstruction and real-time rendering. However, regions with complex textures require numerous Gaussians to capture significant color variations accurately, leading to inefficiencies in rendering speed. To address this challenge, we introduce a hybrid representation for indoor scenes that combines 3DGS with textured meshes. Our approach uses textured meshes to handle texture-rich flat areas, while retaining Gaussians to model intricate geometries. The proposed method begins by pruning and refining the extracted mesh to eliminate geometrically complex regions. We then employ a joint optimization for 3DGS and mesh, incorporating a warm-up strategy and transmittance-aware supervision to balance their contributions seamlessly.Extensive experiments demonstrate that the hybrid representation maintains comparable rendering quality and achieves superior frames per second FPS with fewer Gaussian primitives.","doi":"10.24963/ijcai.2025/128","url":"https://ijcai.org/proceedings/2025/128","pdf":"https://ijcai.org/proceedings/2025/0128.pdf","markdown":"https://ijcai.org/proceedings/2025/128.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/128","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Computer Vision","track":"Main Track","number":128,"pages":{"first":1143,"last":1151},"keywords":["Computer Vision: CV: Representation learning","Computer Vision: CV: 3D computer vision"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}