iiinova — where your digital self keeps evolving

QuacamFM: Quaternion-Constrained Flow Matching for Camera Pose Estimation Bao-Long Tran, Cuong Le, Tahereh Dehdarirad, Fredrik Viksten, Per-Erik Forssén arxiv.org/abs/2609.32455

120

Zhenjun Zhao @ericzzj.bsky.social · 22h

From Feed-Forward to Flow: Unifying Reconstruction and Generation Is Easier Than You Think Haoru Wang, Qianfan Shen, Kai Ye, Wenzheng Chen, Baoquan Chen tl;dr: shared clean-target predictor->feed-forward reconstruction and conditional generation arxiv.org/abs/2609.32761

010

Zhenjun Zhao @ericzzj.bsky.social · 22h

Many Eyes, One World: Feed-Forward 3D Reconstruction from Mixed Cameras Qiaoge Li, Yifan Zhan, Haijun Yang, Haiyang Liu, Yiyi Cai, Chenchi Luo tl;dr: perspective, fisheye and full-panorama images in a single forward pass arxiv.org/abs/2609.35658

021

Zhenjun Zhao @ericzzj.bsky.social · 22h

SLIP-VLA: Single-Step Latent Imagination for Policy Learning in Vision-Language-Action Models Tianfu Li, Haoxuan Xu, Wenbo Chen, Haitian Li, Changchuan Yang, Xinhu Zheng, Jun Ma, Yuan Liu, Lujia Wang, Haoang Li arxiv.org/abs/2609.33575

100

Zhenjun Zhao @ericzzj.bsky.social · 28/09/2026

Light Field Primitive for Novel View Synthesis Liang Chen, Jiahui Ning, Xun Jiang, Xing Xu, Jimmy Ren, Fenglei Fan, Heng Tao Shen tl;dr: scene->primitives defined in two-plane parameterization arxiv.org/abs/2609.31198

000

Zhenjun Zhao @ericzzj.bsky.social · 28/09/2026

VkVIO: Cross-platform GPU Acceleration for Visual-Inertial Odometry with Vulkan Ole Hoffmann, Mateo de Mayo, @dcremers.bsky.social tl;dr: Basalt->Vulkan arxiv.org/abs/2609.30459

000

Zhenjun Zhao @ericzzj.bsky.social · 28/09/2026

TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations Ayush Jain, Sreeharsha Paruchuri, Ishita Gupta, Fan Zhang, Tanner Schmidt, Jakob Engel, Katerina Fragkiadaki, Adam W. Harley arxiv.org/abs/2609.30222

100

Zhenjun Zhao @ericzzj.bsky.social · 24/09/2026

DAVIO: Dense Monocular-Inertial SLAM with Feed-Forward Initialization and Pose-Conditioned Mapping Jaafar Mahmoud, Arthur Movsesyan, Mikhail Iumanov, Sergey Kolyubin tl;dr: DAv3 + OpenVINS arxiv.org/abs/2609.27702

000

Zhenjun Zhao @ericzzj.bsky.social · 24/09/2026

Kairos: Grounded Forecasting of Presence and Directional Flow in 4D Scene Graphs Iacopo Catalano, Julio A. Placed, @jcivera.bsky.social, Jorge Peña Queralta tl;dr: 3DSG->predictive directional-flow memory->4DSG arxiv.org/abs/2609.27467

000

Zhenjun Zhao @ericzzj.bsky.social · 23/09/2026

Dual Covariance Gaussian Splatting SLAM: Decoupling Rendering and Registration for Robust Real-Time Tracking Edward Beng Wai Tan, Siew-Kei Lam tl;dr: each Gaussian has tracking/mapping covariances shared with mean arxiv.org/abs/2609.25746

010

Zhenjun Zhao @ericzzj.bsky.social · 23/09/2026

NaCR: Visual Localization via NeRF-aided Camera Ray Regression Yesheng Zhang, Xiang Dai, Xu Zhao, Chongyang Zhang tl;dr: NeRF + CRR arxiv.org/abs/2609.25907

000

Zhenjun Zhao @ericzzj.bsky.social · 23/09/2026

MatcherCompass: A Deployment-Aware Benchmark to Guide Image Matcher Selection in the Wild Hyunwoo Kim, @giseopkim.bsky.social tl;dr: in title arxiv.org/abs/2609.25688

000

Zhenjun Zhao @ericzzj.bsky.social · 22/09/2026

RegVGGT: Sustainable Visual Geometry Grounding for Streaming via Regulated Memory Hongbo Mao, Junjun Jiang, Youyu Chen, Jiaxin Zhang, Zhemeng Dong, Xianming Liu tl;dr: retain at most 1% tokens per frame to update the context memory arxiv.org/abs/2609.23286

000

Zhenjun Zhao @ericzzj.bsky.social · 22/09/2026

D3GS: Depth, DINO, and RGB Diffusion Co-Guided 3D Gaussian Splatting for Sparse-View Reconstruction Yunqi Gao, Zhanfeng Liao, Hanzhang Tu, Zhaoqi Su, Guoqing Zheng, Songtao Wang, Hongwen Zhang, Zhou Xue, Leyuan Liu, Yebin Liu arxiv.org/abs/2609.22941

110

Zhenjun Zhao @ericzzj.bsky.social · 22/09/2026

VGGT-Prime: Compute-Adaptive Mixture-of-Heads for Efficient Visual Geometry Transformers Abteen Arab, Guile Wu, Chengjie Huang, Dongfeng Bai tl;dr: router->three computation modes for each global-attention head->mean pooling/surrogate attention/softmax attention arxiv.org/abs/2609.23733

000

Zhenjun Zhao @ericzzj.bsky.social · 22/09/2026

Elevator-VIGS: Separating Elevator Motion from Robot Motion in Visual-Inertial Gaussian Splatting SLAM Rui Zhou, Zihan Zhu, Wei Zhang, Zizhou Luo, Norbert Haala, @marcpollefeys.bsky.social tl;dr: VIGS-SLAM->elevator rides arxiv.org/abs/2609.23491

000

Zhenjun Zhao @ericzzj.bsky.social · 22/09/2026

BayesianGS-SLAM: Uncertainty-Aware Neural Rendering SLAM via Probabilistic Formulation Kyeongsu Kang, Seongbo Ha, Sibaek Lee, Hyeonwoo Yu tl;dr: sensor-noise uncertainty + opacity-induced map-representation uncertainty->mapping, tracking, keyframe selection arxiv.org/abs/2609.24140

010

Zhenjun Zhao @ericzzj.bsky.social · 22/09/2026

A Topological Representation with Object-Path Graphs for Open-Vocabulary Instance Navigation Linwei Zheng, Daojie Peng, Bingtao Wang, Haoang Li, Jun Ma tl;dr: object graph->semantic reasoning; path graph->spatial traversal arxiv.org/abs/2609.24189

000

Zhenjun Zhao @ericzzj.bsky.social · 21/09/2026

Robust Structureless Monocular Visual Inertial Initialization Exploiting Line Features and Vanishing Points Junwan Choi, Woongrae Jo, Dong-Uk Seo, Jinwoo Jeon, Hyun Myung arxiv.org/abs/2609.21186

100

Zhenjun Zhao @ericzzj.bsky.social · 21/09/2026

Think Locally, Refine Globally for Memory-Efficient 3D Reconstruction Jingke Zhou, Chenhang Ma, Zhizhou Zhong, Mingkai Liu, Zhuang Zhou, Yicheng ji, Binghua Su, Bo Cai, Xianliang Huang arxiv.org/abs/2609.21437

100

Zhenjun Zhao @ericzzj.bsky.social · 21/09/2026

VoxelTTO: Voxel-Aligned Feed-Forward 3D Gaussian Splatting with Test-Time Optimization Yibin Zhao, Yihan Pan, Yangwen Li, Jun Nan, Jianjun Yi tl;dr: in title arxiv.org/abs/2609.21498

000

Zhenjun Zhao @ericzzj.bsky.social · 21/09/2026

Info3R: Information-Adaptive Test-Time Training for 3D Reconstruction Sunghyun Baek, Hanna Bae, Minchan Kwon, Junmo Kim tl;dr: each frame’s importance->adjust earning rate; cumulative learning rate + prediction confidence->state reset arxiv.org/abs/2609.21938

000

Zhenjun Zhao @ericzzj.bsky.social · 21/09/2026

SFVO: Decoupled Confidence-Guided Stereo-Flow Visual Odometry with Bidirectional PnP Kai Zhang, Guoyang Zhao, Jun Ma tl;dr: disparity and optical flow are converted into forward and backward 3D–2D constraints arxiv.org/abs/2609.21754

000

Zhenjun Zhao @ericzzj.bsky.social · 18/09/2026

GRF-Recon: Global Ray-Field Optimization for Long-Sequence Feed-forward Reconstruction Enpeng Li, Yunzhou Zhang, Zhiyao Zhang, Dexuan Lyu, Chenyu Wang, Chiyuan Cui, Cheng Cheng arxiv.org/abs/2609.20012

100

Zhenjun Zhao @ericzzj.bsky.social · 18/09/2026

Can 4D Foundation Models Remember? Guangzhao He, Hadar Averbuch-Elor, Wei-Chiu Ma tl;dr: benchmark->visual memory in 4D foundation models arxiv.org/abs/2609.20819

010

Zhenjun Zhao @ericzzj.bsky.social · 18/09/2026

AMB3R-SLAM: Kilometer-scale SLAM with Hierarchical Backend Hengyi Wang, Lourdes Agapito tl;dr: AMB3R->SLAM arxiv.org/abs/2609.19518

000

Zhenjun Zhao @ericzzj.bsky.social · 18/09/2026

EliGSiR: Continual RGB-D Mapping with Gaussian Splatting under Bounded Compute Björn Ellensohn, Elmar Rueckert, Christian Rauch tl;dr: bounded compute->view scheduling, supervision fidelity, geometry growth arxiv.org/abs/2609.20348

000

Zhenjun Zhao @ericzzj.bsky.social · 18/09/2026

VGGT-GS SLAM: Uncalibrated Monocular Gaussian Splatting SLAM with Feed-Forward Priors Yuhang Han, Hao Wang, Jiaxi Cao, Xingyu Liu tl;dr: VGGT->GS->submap differentiable BA; submap alignment and SALAD-based loop->Gaussian alignment->scale refinement arxiv.org/abs/2609.19628

000

Zhenjun Zhao @ericzzj.bsky.social · 18/09/2026

SLAMSqueezeBench: Comparing SLAM Systems under Resource Constraints Mohamed Hefny, Karthik Dantu, Steven Y. Ko tl;dr: in title arxiv.org/abs/2609.19533

000

Zhenjun Zhao @ericzzj.bsky.social · 17/09/2026

IRIS: Implicit Rendering Matters for Pose-Free Novel View Synthesis Wenyu Li, Sidun Liu, Peng Qiao, Yong Dou, Tongrui Hu tl;dr: latent neural field; reference views->projected features->sampled 3D points->point-wise latent features->rendering arxiv.org/abs/2609.18034

000

Zhenjun Zhao @ericzzj.bsky.social · 17/09/2026

GeoCond: A Conditioning-Aware Reliability Adapter for Feed-Forward 3D Reconstruction David Ahmedt-Aristizabal, Mohammad Ali Armin, Russell Tsuchida, Lars Petersson arxiv.org/abs/2609.18465

100

Zhenjun Zhao @ericzzj.bsky.social · 17/09/2026

Function-Preserving Data Generation for Zero-Shot Real-to-Sim-to-Real Manipulation Tianyi Xiang, Xupeng Xie, Jiahang Cao, Andrew F. Luo, Haoang Li, Jun Ma tl;dr: in title arxiv.org/abs/2609.18293

000

Zhenjun Zhao @ericzzj.bsky.social · 17/09/2026

ActiveScale: Scaling Active Perception for Robots across Model, Data, and Hardware Shuai Zhou, Kaisheng Pang, Wenxuan Song, Wenjie Zhang, Xinhu Zheng, Haoang Li tl;dr: pose-grounded temporal VLA for active perception and cross-view reasoning arxiv.org/abs/2609.18514

000

Zhenjun Zhao @ericzzj.bsky.social · 17/09/2026

From Gameplay to Policy: Towards Scalable Robot Data Collection via Gamified Robot-Free Interaction tl;dr: VR-based gamified egocentric data collection platform arxiv.org/abs/2609.18650

100

Zhenjun Zhao @ericzzj.bsky.social · 16/09/2026

FFVO: A Feedforward Pose Decoder for Long-Horizon Visual Odometry Meng-Li Shih, Shih-Yang Su, Yuliang Zou, Hao Xiang, Haidong Zhu, Vincent Casser, Brian Curless, Dmitry Kalenichenko, Mingxing Tan, Dragomir Anguelov arxiv.org/abs/2609.13733

110

Zhenjun Zhao @ericzzj.bsky.social · 16/09/2026

MomentBA: Second-order Spatial Moments for Anisotropic Correspondence Uncertainty in Differentiable Bundle Adjustment Yuqing Wang, Xiaoji Niu, Yan Wang, Hailiang Tang, Jian Kuang, Tisheng Zhang arxiv.org/abs/2609.13691

130

Zhenjun Zhao @ericzzj.bsky.social · 16/09/2026

Filling the Unseen: Scene Extrapolation via 3D Gaussian Splatting Yunlai Zhou, Yiren Lu, Tuo Liang, Disheng Liu, Vipin Chaudhary, Yu Yin tl;dr: independent camera view detection->hierarchical two-stage extrapolation arxiv.org/abs/2609.13262

020

Zhenjun Zhao @ericzzj.bsky.social · 16/09/2026

ConeGaussian: Anti-Aliased Gaussian Ray-Tracing for Generic Central Cameras Deheng Zhang, Letian Shi, Runyi Yang, Zhendong Li, Lei Sun, Kanzhi Wu, Ajad Chhatkuli, Danda Pani Paudel, Luc Van Gool tl;dr: closed-form anisotropic pixel footprint filter arxiv.org/abs/2609.13397

000

Zhenjun Zhao @ericzzj.bsky.social · 16/09/2026

RIGOR: Rig-Informed Geometry for Omnidirectional Reconstruction Tingjun Huang, Dmitry Rudshin, Mathieu Meyer, @pietrobonazzi.bsky.social, @marcpollefeys.bsky.social, Emilia Szymańska arxiv.org/abs/2609.13504

180

Zhenjun Zhao @ericzzj.bsky.social · 16/09/2026

Robust Multi-Model Fitting through Learning Neighbor Regions Chang Nie, Guangming Wang, Zhe Liu, Hesheng Wang tl;dr: random minimum set sampling + confidence-based selection->good minimum sets->coarse-hypotheses->region features-> fine-hypotheses arxiv.org/abs/2609.15348

050

Zhenjun Zhao @ericzzj.bsky.social · 16/09/2026

SCOUT-SLAM: Structurally-Coupled Dual Uncertainty-Aware 3DGS SLAM in the Wild Kumaran Karthik, Pramat Shastri Jois, Suresh Sundaram tl;dr: one model->tracking and per-pixel uncertainties arxiv.org/abs/2609.14634

020

Zhenjun Zhao @ericzzj.bsky.social · 16/09/2026

Closed-form Bayesian homography estimation from noisy point correspondences Hanne Beuter, Sebastian Dorn tl;dr: posterior mean of homography->closed-form solver->iterative Bayesian approach for non-linearities; homography parameters and uncertainty->posterior distribution arxiv.org/abs/2609.15227

000

Zhenjun Zhao @ericzzj.bsky.social · 16/09/2026

FujinSplat: Seeing Through Smoke with RAW-Domain Gaussian Splatting Gengjia Chang, Ziteng Cui, Shuhong Liu tl;dr: calibrated camera ISP + bounded Monotone Color Flow->RAW-domain GS for dehazing arxiv.org/abs/2609.06017

000

Zhenjun Zhao @ericzzj.bsky.social · 16/09/2026

SURE-Map: Self-Correcting Streaming Geometric Foundation Model Mingkai Liu, Hao Zhao, Xingxing Zuo tl;dr: LingBot-Map + uncertainty head; geometry-context-attention + full-attention->scale recalibration arxiv.org/abs/2609.15795

000

Zhenjun Zhao @ericzzj.bsky.social · 10/09/2026

AVSplat: Dense-View Feed-Forward 3D Gaussian Splatting with Assist-View Preconditioning Muyu Xu, Fangneng Zhan, Yu Wei, Hanspeter Pfister, Shijian Lu tl;dr: condition each view before global aggregation; adapt voxel weights to occupancy and reliability arxiv.org/abs/2609.05925

021

Zhenjun Zhao @ericzzj.bsky.social · 10/09/2026

Radiation, Rotation and Scale Invariant Feature Descriptor for Multimodal Image Matching Yuanxin Ye, Tengfeng Tang, Tao Peng, Zhiqiang Han, Jiayuan Li, Mi Wang tl;dr: DHRS + RRSI descriptor + cross-modal generative reconstruction arxiv.org/abs/2609.06343

020

Zhenjun Zhao @ericzzj.bsky.social · 10/09/2026

Point4D: Long-range 4D Motion Reconstruction Minsik Jeon, Jay Karhade, Deva Ramanan, Shubham Tulsiani tl;dr: re-query predicted 3D endpoint directly in the next chunk arxiv.org/abs/2609.09145

000

Zhenjun Zhao @ericzzj.bsky.social · 10/09/2026

Learning Global Camera Poses from Noisy View-Graphs for Structure from Motion Fadi Khatib, Meirav Galun, Ronen Basri tl;dr: self-supervised permutation-equivariant GNN->pose averaging arxiv.org/abs/2609.09491

010

Zhenjun Zhao @ericzzj.bsky.social · 10/09/2026

RoMa-Ω: What Feed-Forward 3D Models Know About Image Matching @davnords.bsky.social, Xinyue Zhang, @thibautloiseau.bsky.social, @vincentlepetit.bsky.social, @fredkahl.bsky.social tl;dr: replace the DINOv3 in RoMa v2 with features from the VGGT-Ω arxiv.org/abs/2609.09507

050

Zhenjun Zhao @ericzzj.bsky.social · 10/09/2026

MAC-I2: Learned Metrics-Aware Covariance for Robust Visual-Inertial Fusion in Initialization and Calibration Xiang Fei, @yuhengqiu.bsky.social, Can Xu, Yutian Chen, Ruogu Li, Xingxing Zuo, Wenshan Wang, @smash0190.bsky.social arxiv.org/abs/2609.07116

120