Reliability-Regulated Trajectory Optimization for Progressive COLMAP-Free 3D Gaussian Splatting

Zijian Wu; Jinliang Wang; Zidian Lin; Ying Song; Ziqian Lu; Hanjie Ma; Zhen Ye; Mingfeng Jiang

cs.CVSep 25, 2026

Reliability-Regulated Trajectory Optimization for Progressive COLMAP-Free 3D Gaussian Splatting

Authors: Zijian Wu, Jinliang Wang, Zidian Lin, Ying Song, Ziqian Lu, Hanjie Ma, Zhen Ye, Mingfeng Jiang

Organizations: School of Computer Science and Technology, Zhejiang Sci-Tech University · School of Biomedical Engineering, Tsinghua University · CardioCloud Medical Technology (Beijing) Co., Ltd. · Lishui University ·

Abstract

COLMAP-free 3D Gaussian Splatting (3DGS) bypasses computationally expensive structure-from-motion (SfM) pipelines, yet progressive camera pose tracking remains fundamentally vulnerable to error compounding---early pairwise tracking inaccuracies both corrupt subsequent frame initializations and remain permanently frozen in the scene representation. Rather than relying on heavyweight external neural priors or treating progressive tracking through isolated heuristic fixes, we propose a unified reliability-regulated trajectory optimization framework for progressive COLMAP-free 3DGS. At its core, our framework establishes an intrinsic, self-supervised bidirectional cycle-consistency mechanism that systematically regulates progressive camera trajectory estimation across two complementary temporal horizons: (1) Forward Motion Propagation, where the online reliability signal adaptively gates first-order kinematic warm-starts of rigid motion into upcoming pairwise registrations, supplying informed directional search priors while safely intercepting untrusted transitions; and (2) Retrospective Trajectory Correction, where the same reliability signal dynamically weights relative-pose consistency constraints within a sliding window of neighboring camera poses. By governing both prospective state initialization and retrospective trajectory consolidation through a unified reliability regulator, our self-contained framework resolves progressive drift without external priors or offline preprocessing. Extensive evaluations on Tanks and Temples and CO3D-V2 benchmarks show that our method substantially improves camera trajectory accuracy and novel-view rendering quality, outperforming existing unposed baselines. Code is available at https://github.com/Zijian1026/RRTO-CF3DGS.

Figures & tables

Figure 1: Qualitative comparison on novel-view synthesis and camera trajectory estimation. Our reliability-regulated trajectory optimization prevents local error compounding along the sequence and eliminates trajectory drift relative to CF-3DGS.

Figure 2: Overview of the proposed reliability-regulated trajectory optimization framework. Given an unposed image sequence, our framework establishes an intrinsic bidirectional cycle-consistency signal to systematically regulate progressive camera estimation across two complementary temporal phases: (a) Forward Motion Propagation , where tracking confidence adaptively gates first-order kinematic extrapolation on $\mathrm{SE}(3)$ to supply an informed warm-start while intercepting corrupted priors; and (b) Retrospective Trajectory Correction , where camera poses within a sliding window are jointly optimized under fixed Gaussian geometry, constrained by multi-view photometric alignment and confidence-weighted relative pose consistency. Shared cycle reliability ensures that noisy transitions neither corrupt future registrations nor distort local window trajectory refinement.

Figure 3: Qualitative novel-view synthesis results on the Tanks and Temples benchmark. We compare our method against unposed baselines. While existing methods exhibit severe blurring, missing structures, and geometric distortion due to noisy or drifted pose estimates, our approach produces photorealistic renderings with fine-grained textures and sharp edges. Inset red and green boxes highlight key detailed regions.

Scene	Nope-NeRF [ 17 ]			CF-3DGS [ 18 ]			HT-3DGS [ 22 ]			PCR-GS [ 23 ]			Ours
Scene	PSNR	SSIM	LPIPS	PSNR	SSIM	LPIPS	PSNR	SSIM	LPIPS	PSNR	SSIM	LPIPS	PSNR	SSIM	LPIPS
Ballroom	24.43	0.71	0.28	24.92	0.83	0.12	25.62	0.85	0.11	25.16	0.83	0.12	28.16	0.91	0.07
Barn	23.00	0.61	0.40	19.26	0.57	0.38	20.33	0.56	0.35	19.00	0.53	0.46	22.01	0.67	0.27
Church	23.01	0.65	0.37	26.83	0.87	0.14	27.80	0.89	0.12	27.31	0.89	0.13	27.53	0.89	0.12
Family	24.59	0.71	0.35	25.03	0.85	0.16	27.80	0.89	0.12	27.15	0.90	0.12	28.31	0.91	0.11
Francis	23.01	0.66	0.43	23.90	0.74	0.27	24.31	0.72	0.26	24.77	0.73	0.26	25.96	0.77	0.25

Table 1: Quantitative novel view synthesis results on the Tanks and Temples benchmark with stride 5. Held-out test views are evaluated using PSNR

\uparrow

, SSIM

\uparrow

, and LPIPS

\downarrow

. Best results are bolded.

Figure 4: Qualitative comparison on challenging 360-degree object-centric sequences from CO3D-V2. On the displayed sequences with wide baselines and continuous rotational trajectories, competing methods exhibit trajectory deviations and rendering artifacts such as floaters and blurriness. Our reliability-regulated framework produces more accurate trajectory estimates and higher-fidelity Gaussian reconstructions.

Method	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$
CF-3DGS [ 18 ]	26.11	0.782	0.270
HT-3DGS [ 22 ]	26.59	0.800	0.260
PCR-GS [ 23 ]	26.16	0.785	0.272
Ours	27.71	0.819	0.239

Table 2: Average novel view synthesis results on the CO3D-V2 dataset. Test views are evaluated using PSNR

\uparrow

, SSIM

\uparrow

, and LPIPS

\downarrow

. Best results are bolded.

Scene	Nope-NeRF [ 17 ]			CF-3DGS [ 18 ]			HT-3DGS [ 22 ]			PCR-GS [ 23 ]			Ours
Scene	$\text{RPE}_{t}$	$\text{RPE}_{r}$	ATE	$\text{RPE}_{t}$	$\text{RPE}_{r}$	ATE	$\text{RPE}_{t}$	$\text{RPE}_{r}$	ATE	$\text{RPE}_{t}$	$\text{RPE}_{r}$	ATE	$\text{RPE}_{t}$	$\text{RPE}_{r}$	ATE
Ballroom	0.127	0.247	0.002	0.279	0.048	0.006	0.279	0.047	0.006	0.295	0.059	0.006	0.122	0.026	0.002
Barn	1.343	0.403	0.033	2.409	0.585	0.065	2.252	0.574	0.057	3.379	1.074	0.118	0.576	0.314	0.011
Church	0.490	0.127	0.044	0.081	0.095	0.004	0.081	0.095	0.004	0.070	0.092	0.005	0.053	0.087	0.003
Family	0.119	0.052	0.003	0.775	0.294	0.011	0.203	0.118	0.004	0.483	0.187	0.006	0.455	0.181	0.006
Francis	2.941	1.515	0.079	0.814	0.916	0.021	0.733	0.878	0.016	0.714	0.816	0.015	0.416	0.747	0.015

Table 3: Quantitative camera pose estimation results on the Tanks and Temples benchmark with stride 5. Trajectories are evaluated using

\text{RPE}_{t}

\downarrow

(

\times 10^{2}

\text{RPE}_{r}

\downarrow

( ∘ ), and ATE

\downarrow

. Best results are bolded.

Method	$\text{RPE}_{t}$ $\downarrow$	$\text{RPE}_{r}$ $\downarrow$	ATE $\downarrow$
CF-3DGS [ 18 ]	0.579	0.548	0.023
HT-3DGS [ 22 ]	0.545	0.511	0.022
PCR-GS [ 23 ]	0.658	0.842	0.032
Ours	0.352	0.382	0.014

Table 4: Average camera pose estimation results on the CO3D-V2 dataset. Trajectories are evaluated using

\text{RPE}_{t}

\downarrow

(

\times 10^{2}

\text{RPE}_{r}

\downarrow

( ∘ ), and ATE

\downarrow

. Best results are bolded.

Figure 5: Reliability verification of bidirectional cycle-consistency confidence. We visualize the temporal trajectory error against the estimated cycle-consistency confidence $c_{i}$ across representative sequences from Tanks and Temples ( A : Family , B : Horse ) and CO3D-V2 ( C : Apple , D : Book ). For each sequence, the upper subplot shows the frame-wise bidirectional confidence $c_{i}$ , while the lower subplot displays the corresponding translational error and rotational discrepancy.

Variant	Controls			Loss Weight	Rendering quality			Pose accuracy
Variant	MP	Gate	WJ	Loss Weight	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	$\text{RPE}_{t}\downarrow$	$\text{RPE}_{r}\downarrow$	$\text{ATE}\downarrow$
CF-3DGS (sequential)	$\times$	–	$\times$	–	21.93	0.709	0.250	1.327	0.695	0.024
WJ, photometric only	$\times$	–	$\checkmark$	–	22.56	0.724	0.247	1.047	0.623	0.022
WJ + Uniform loss weight	$\times$	–	$\checkmark$	Uniform	22.74	0.726	0.242	0.998	0.618	0.021
WJ + F–B loss weight	$\times$	–	$\checkmark$	F–B	22.97	0.729	0.237	0.920	0.610	0.019
Ungated MP	$\checkmark$	$\times$	$\times$	–	23.58	0.752	0.210	0.714	0.476	0.016

Table 5: Ablation study and reliability calibration on Tanks and Temples. We evaluate the impact of motion-guided initialization (MP), confidence gating (Gate), window joint refinement (WJ), and forward–backward (F–B) consistency weighting.

\text{RPE}_{t}

is reported in

\times 10^{2}

and

\text{RPE}_{r}

in degrees.

3D Gaussian Splatting

3D Gaussian Splatting represents scenes as optimizable 3D Gaussian primitives for fast, photorealistic rendering from new viewpoints.

See all 1,000 papers

CrossFit-GS: Out-of-Fold Pose Estimation for COLMAP-Free 3D Gaussian Splatting
Oct 20, 2026Zijian Wu, Jinliang Wang, Mingfeng Jiang +33D Gaussian Splatting 3D Reconstruction
Zhejiang Sci-Tech University · Tsinghua University
GloSplat: Joint Pose-Appearance Optimization for Faster and More Accurate 3D Reconstruction
Mar 5, 2026Tianyu Xiong, Rui Li, Linjie Li +13D Reconstruction 3D Gaussian Splatting
Department of Computer Science, Northwestern Polytechnical University, Shanxi, China · CEMSE, KAUST, Thuwal, Jeddah
DeltaSplat: Iterative Gaussian Refinement for Pose-Free Feed-Forward 3D Gaussian Splatting
Oct 7, 2026Chanung Park, Seunghyeon Song, Joo Chan Lee +23D Gaussian Splatting 3D Reconstruction
Department of Electrical and Computer Engineering, Sungkyunkwan University · Department of Artificial Intelligence, Sungkyunkwan University · Department of Artificial Intelligence, Yonsei University

Oct 20, 2026J/K move · Enter open · S save

CrossFit-GS: Out-of-Fold Pose Estimation for COLMAP-Free 3D Gaussian Splatting

Zijian Wu, Jinliang Wang, Mingfeng Jiang, Zidian Lin+2

Zhejiang Sci-Tech University · Tsinghua University

3D Gaussian Splatting 3D Reconstruction Camera Pose Estimation Novel View Synthesis

Open paper AskPDF arXiv

Pose-free 3D Gaussian Splatting (3DGS) aims to bypass cumbersome Structure-from-Motion (SfM) by directly reconstructing scenes from unposed image sequences. In this work, we present CrossFit-GS, a deferred-commitment progressive framework that mitigates cumulative trajectory drift and breaks the self-reinforcing loop of distorted-map error propagation. Specifically, we partition the input sequence into interleaved subsets and maintain two complementary submaps. Each candidate pose is cross-refined against a frozen opposite submap that has never been optimized using the target frame, thereby providing an independent geometric reference for pose estimation. Checkerboard validation and spatial coverage safeguards further reject unreliable updates, and only verified poses are committed to their corresponding owner submap. Once the trajectory has been refined, the intermediate submaps are discarded and the final global representation is trained from scratch using the fixed refined poses. Extensive evaluations across multiple benchmarks demonstrate that CrossFit-GS substantially reduces cumulative trajectory drift and consistently improves both camera pose estimation and novel-view synthesis over existing methods.

Abstract

3D Gaussian Splatting

Explore similar work

CrossFit-GS: Out-of-Fold Pose Estimation for COLMAP-Free 3D Gaussian Splatting

GloSplat: Joint Pose-Appearance Optimization for Faster and More Accurate 3D Reconstruction

DeltaSplat: Iterative Gaussian Refinement for Pose-Free Feed-Forward 3D Gaussian Splatting