RawSLAM introduces the first online Gaussian SLAM framework that operates directly on single‑exposure 16‑bit linear HDR images, overcoming the limitations of traditional 8‑bit LDR SLAM systems in extreme lighting. The approach combines an HDR Gaussian splatting module with a Reinhard‑compressed photometric objective and structure‑guided spatial weighting, achieving superior trajectory and reconstruction accuracy compared to a direct HDR adaptation of MonoGS. The same formulation also improves performance on standard 8‑bit inputs and can be transferred to other SLAM systems such as SplaTAM, Gaussian SLAM, and DROID‑W, eliminating tracking failures in challenging illumination sequences. Additionally, RawSLAM provides a new dataset of 10 real‑world indoor sequences with 16‑bit RAW imagery, depth, IMU, and OptiTrack poses.
arXiv:2609.21347v1 Announce Type: new Abstract: Recent progress in 3D Gaussian Splatting (3DGS) has enabled dense visual SLAM with pinhole cameras, yet most pipelines are not designed for panoramic i...
Existing Gaussian-splatting-based monocular Simultaneous Localization and Mapping (SLAM) systems are either tailored to short sequences, are not real-time, or suffer from prohibitive GPU memory requirements, limiting their applicability in realistic, long-horizon scenarios. To address this, we present GLAM-SLAM, a real-time, decoupled Gaussian-splatting SLAM system designed for large-scale outdoor scenes.
InstantHDR is a feed-forward network that initializes high dynamic range (HDR) 3D scenes from uncalibrated multi-exposure low dynamic range (LDR) image collections in a single forward pass. It uses geometry-guided appearance modeling for multi-exposure fusion and a meta-network for scene-specific tone mapping. The authors also created a pre-training dataset, HDR-Pretrain, with 168 Blender-rendered scenes to support generalizable HDR models, achieving a speedup of about 700× over state‑of‑the‑art optimization methods while maintaining comparable quality after lightweight post‑optimization.
DrawSplat is an Atlanta World-guided implicit Gaussian SLAM framework designed for indoor reconstruction. It first sketches structural layout using explicit point-line geometry, then refines appearance and geometry with implicit neural Gaussians. The method jointly tracks camera poses, sparse geometry, and gravity, infers structural planes, and allocates Gaussian capacity to informative regions, achieving robust tracking, high-fidelity rendering, and strong geometric reconstruction while balancing quality, efficiency, and model size.
arXiv:2601.15951v2 Announce Type: replace Abstract: Novel view synthesis (NVS) of static and dynamic urban scenes is essential for autonomous driving simulation, yet existing methods often struggle t...
arXiv:2609.17387v1 Announce Type: new Abstract: Real-time dense SLAM is a core capability for robotics applications that require robust localization and high- quality mapping in dynamic or fast-chang...
arXiv:2608.29003v1 Announce Type: cross Abstract: In dynamic and unstructured environments, conventional SLAM systems generally suffer from significant accuracy degeneration due to their static assum...
VoxelTTO is a feed‑forward framework that reconstructs 3D Gaussian splatting scenes from multiple images by aggregating dense image features into a global voxel representation and decoding Gaussians from voxel features, thereby eliminating the pixel‑to‑Gaussian correspondence. It incorporates test‑time optimization with lightweight LoRA modules to adapt to known camera parameters while keeping the pretrained visual foundation model frozen. The method replaces standard rasterization with stochastic solid volume rendering, improving geometric fidelity, and demonstrates superior RGB‑D novel‑view synthesis and camera‑pose estimation on Replica, Tanks and Temples, and DTU datasets.
The paper introduces LingGS, an online monocular RGB Gaussian splatting SLAM system that decouples feed‑forward geometry prediction from camera tracking. By leveraging a frozen streaming 3D foundation model as a virtual RGB‑D sensor for depth estimation and an explicit geometric solver for camera motion via feature reprojection, LingGS achieves higher tracking accuracy than learned predictions. Experiments on indoor and outdoor datasets demonstrate significant improvements in reconstruction quality, achieving about 7 FPS on a single RTX 4090 and 2–3× the throughput of prior SLAM systems.
arXiv:2608. 15024v1 Announce Type: cross Abstract: Current Vision-based SLAM systems fail catastrophically when motion blur corrupts the visual input, as they attempt the ill-posed inverse problem of recovering sharp content from degraded observations.
CGS‑SLAM is a hybrid decentralized/centralized SLAM system that enables multi‑agent 3D Gaussian Splatting reconstruction using only RGB images and inertial data. Each agent locally tracks motion with inertial priors, builds a scaled map via a monocular depth estimator, and shares keyframe encodings to facilitate dynamic keyframing and submap alignment. A central server then aligns submaps with a view‑alignment model, keeping communication costs low while achieving competitive tracking, higher rendering quality, and accurate submap alignment in GNSS‑denied environments.
arXiv:2611.07081v1 Announce Type: new Abstract: Multi-perspective-camera systems are widely adopted since they provide broad visual coverage for autonomous driving, motivating the synthesis of a unif...