Huaizhen Wang

Prof. Huaizhen Wang


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 August 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
YWYingcai Wan
Yingcai Wan
BWBaoyu Wang
Baoyu Wang
JXJiqian Xu
Jiqian Xu
YGYue Gao
Yue Gao
HWHuaizhen Wang
Huaizhen Wang
Monocular Gaussian SLAM must recover camera motion, surface structure, and appearance from an RGB sequence without metric depth input or benchmark geometry during reconstruction. This setting is challenged by scale-ambiguous predictions, spatially varying reliability, and the tendency of an unconstrained Gaussian map to absorb pose and depth errors into its geometric and appearance parameters. We present Mono3DGS-SLAM, a reliability-guided Gaussian–TSDF framework with a sequence-precalibrated prediction stage and an incremental mapping backend. Deterministic reliability gates select admissible observations, while one frozen scale jointly transports predicted depth, camera translation, and length-valued mapping parameters into an internally consistent canonical coordinate. A confidence-weighted colorized TSDF stores the persistent surface, base color, and visibility support. A capacity-bounded Gaussian layer is restricted to reliable residual regions and primarily restores appearance detail over the fused surface. On Replica, Mono3DGS-SLAM achieves 0.249 cm mean ATE and is most accurate in five of eight scenes. With identical poses, depths, and views, the hybrid output reaches 30.678 dB PSNR, exceeding either component alone. ScanNet and TUM-RGBD results further assess transfer to real monocular sequences.

25 August 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
YWYingcai Wan
Yingcai Wan
HWHuaizhen Wang
Huaizhen Wang
JXJiqian Xu
Jiqian Xu
YGYue Gao
Yue Gao
BWBaoyu Wang
Baoyu Wang
Monocular reconstruction under severe low light is ill-posed because underexposure removes repeatable texture, view-dependent camera processing violates photometric consistency, and pose or depth errors can be absorbed as blurred or distorted Gaussian primitives. We propose LL-3DGS Reconstruction, a coupled geometric–photometric framework that estimates a canonical normally illuminated Gaussian scene while retaining raw low-light observations as explicit evidence. Its geometry front end preserves view identity and order, selects a raw or fixed enhanced stream for learned multi-view inference, and converts the estimated cameras, depth, and points into a density-aware Gaussian seed with optional Sim(3) co-registration. The Gaussian back end constrains one shared 3D field through a bounded luminance restoration path and a low-light re-degradation path, preventing independent per-view corrections from becoming inconsistent scene content. Dark-region weighting, reliability-aware supervision, staged activation, bounded densification, and scale–anisotropy constraints further regularize flexible Gaussian primitives against noise, illumination errors, and weak geometry. Finally, co-registered metric depth supplies surface geometry while the canonical Gaussian rendering supplies restored color for colored-point and TSDF fusion. With paired normal-light supervision, the method obtains 25.44 dB PSNR, 0.898 SSIM, and 0.247 LPIPS on five LOM scenes and averages 21.195 dB, 0.449 SSIM, and 0.523 LPIPS across eight LLRS scenes. A controlled LOM-sofa ablation shows that low-light consistency supports observation explainability, while four-scene TSDF outputs document the explicit reconstruction path without claiming geometric accuracy in the absence of 3D ground truth.

22 September 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YWYingcai Wan
Yingcai Wan
BWBaoyu Wang
Baoyu Wang
JXJiqian Xu
Jiqian Xu
YGYue Gao
Yue Gao
HWHuaizhen Wang
Huaizhen Wang
Monocular Gaussian SLAM must recover camera motion, surface structure, and appearance from an RGB sequence without metric depth input or benchmark geometry during reconstruction. This setting is challenged by scale-ambiguous predictions, spatially varying reliability, and the tendency of an unconstrained Gaussian map to absorb pose and depth errors into its geometric and appearance parameters. We present Mono3DGS-SLAM, a reliability-guided Gaussian–TSDF framework with a sequence-precalibrated prediction stage and an incremental mapping backend. Deterministic reliability gates select admissible observations, while one frozen scale jointly transports predicted depth, camera translation, and length-valued mapping parameters into an internally consistent canonical coordinate. A confidence-weighted colorized TSDF stores the persistent surface, base color, and visibility support. A capacity-bounded Gaussian layer is restricted to reliable residual regions and primarily restores appearance detail over the fused surface. On Replica, Mono3DGS-SLAM records 0.249 cm mean ATE in the evaluated runs and has lower ATE in five of eight scenes within the locally evaluated monocular group. With identical poses, depths, and views, the hybrid output reaches 30.678 dB PSNR in a paired comparison of outputs from the same hybrid runs. This comparison does not establish superiority over independently optimized single-representation systems. The evaluated full pipeline uses future observations and does not establish online or real-time SLAM performance. ScanNet and TUM-RGBD results further assess transfer to real monocular sequences.