The Year in AI Papers
The year/Topics/3D and spatial intelligence

Research collection

3D and spatial intelligence

3D and 4D scene generation, reconstruction, spatial reasoning, point clouds, and 3D detection or perception.

Papers
29
Research labs
3
Official code
28

1–29 of 29 papers in this collection

01

Independent research

PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space

PixWorld is a unified pixel-space diffusion framework for 3D scene generation and reconstruction. It partitions multi-view inputs into clean and noisy subsets, processes them with a two-stream diffusion transformer, and decodes features into a pixel-aligned 3D Gaussian representation. The diffusion objective is applied directly on rendered images,…

Sensen Gao, Zhaoqing Wang, Qihang Cao, Dongdong Yu, et al.
Published
Jul 2026
Citations
1
Code
239 stars
Read summary Original
02

NVIDIA

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

SpatialClaw is a training-free framework that improves spatial reasoning in vision-language models (VLMs) by using code as the action interface. It maintains a persistent Python kernel pre-loaded with input frames and perception tools, allowing a VLM-backed agent to write and execute one code cell per step, inspect intermediate results (e.g., masks, depth…

Seokju Cho, Ryo Hachiuma, Abhishek Badki, Hang Su, et al.
Published
Jun 2026
Citations
3
Code
358 stars
Read summary Original
03

Independent research

ABot-Earth 0.5: Generative 3D Earth Model

ABot-Earth 0.5, developed by AMAP CV Lab (Alibaba Group), is a generative 3D framework that synthesizes vast, seamless 3D environments from geospatially referenced satellite imagery using a native 3D Gaussian Splatting (3DGS) representation. Trained on real-world urban reconstructions, it generates realistic geometry and textures at under 10 minutes per…

Ming Qian, Tianjian Ouyang, Mingchao Sun, Zijian Wang, et al.
Published
Jun 2026
Citations
1
Code
192 stars
Read summary Original
04

NVIDIA

Why Far Looks Up: Probing Spatial Representation in Vision-Language Models

The paper investigates whether vision-language models (VLMs) achieve spatial reasoning through structured 3D understanding or by exploiting statistical shortcuts in natural images. The authors introduce a representation-level analysis framework using contrastive pairs to measure how spatial axes (horizontal, vertical, depth) are organized in VLM…

Cheolhong Min, Jaeyun Jung, Daeun Lee, Hyeonseong Jeon, et al.
Published
May 2026
Citations
1
Code
16 stars
Read summary Original
05

arXiv.org

SpatialBench: Is Your Spatial Foundation Model an All-Round Player?

SpatialBench is a new benchmark for evaluating spatial foundation models across diverse domains, input densities, and model paradigms. It includes 19 datasets, 546 scenes, 41 model variants, and 6 paradigms, using a deterministic multi-density sampling protocol (single, sparse, medium, dense). Key findings reveal that full-context attention models achieve…

Haosong Peng, Hao Li, Jiaqi Chen, Yuhao Pan, et al.
Published
May 2026
Citations
0
Code
119 stars
Read summary Original
06

arXiv.org

TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation

TransitLM is a large-scale dataset of over 13 million transit route planning records from four Chinese cities (Beijing, Shanghai, Shenzhen, Chengdu), covering 120,845 stations and 13,666 lines. It is released as a continual pre-training corpus and benchmark data for three tasks: optimal route generation, preference-aware planning, and multi-route…

Hanyu Guo, Jiedong Yang, Chao Chen, Longfei Xu, et al.
Published
May 2026
Citations
0
Code
125 stars
Read summary Original
07

arXiv.org

PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects

PhysX-Omni is a unified framework for generating simulation-ready physical 3D assets covering rigid, deformable, and articulated objects. It introduces a novel template-based run-length encoding (RLE) geometry representation for Vision-Language Models, which directly encodes high-resolution 3D structures without special tokens or segmentation modules,…

Ziang Cao, Yinghao Liu, Haitian Li, Runmao Yao, et al.
Published
May 2026
Citations
1
Code
307 stars
Read summary Original
08

arXiv.org

RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments

RADIO-ViPE is an online, calibration-free semantic SLAM system that processes raw monocular RGB video to produce geometry-aware, open-vocabulary 3D grounding. It tightly couples multi-modal embeddings from agglomerative foundation models (RADIO/RADSeg) with geometric information within a dense bundle adjustment framework, using a factor graph with…

Zaid Nasser, Mikhail Iumanov, Tianhao Li, Maxim Popov, et al.
Published
Apr 2026
Citations
0
Code
138 stars
Read summary Original
09

arXiv.org

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

HY-World 2.0 is an open-source multi-modal world model framework that unifies 3D world generation and reconstruction. For sparse inputs (text or single-view images), it generates navigable 3D Gaussian Splatting (3DGS) scenes via a four-stage pipeline: panorama generation (HY-Pano 2.0), trajectory planning (WorldNav), world expansion (WorldStereo 2.0), and…

Team HY-World, Chenjie Cao, Xuhui Zuo, Zhenwei Wang, et al.
Published
Apr 2026
Citations
19
Code
2.5K stars
Read summary Original
10

arXiv.org

SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments

SpatialEvo introduces a self-evolving framework for 3D spatial reasoning that replaces model consensus with deterministic geometric feedback. The core contribution is the Deterministic Geometric Environment (DGE), which defines validation rules for 16 spatial reasoning task categories and computes exact ground truth from point clouds and camera poses,…

Dinging Li, Yingxiu Zhao, Xinrui Cheng, Kangheng Lin, et al.
Published
Apr 2026
Citations
3
Code
80 stars
Read summary Original
11

ACM Transactions on Graphics

Strips as Tokens: Artist Mesh Generation with Native UV Segmentation

The paper introduces Strips as Tokens (SATO), a framework for generating artist-quality 3D meshes with native UV segmentation using autoregressive transformers. SATO uses a strip-based tokenization strategy that serializes meshes as connected chains of faces, preserving edge flow and structural regularity. This unified representation allows the same token…

Rui Xu, Dafei Qin, Kaichun Qiao, Qiujie Dong, et al.
Published
Apr 2026
Citations
2
Code
181 stars
Read summary Original
12

arXiv.org

WildDet3D: Scaling Promptable 3D Detection in the Wild

WildDet3D introduces a unified, geometry-aware architecture for open-vocabulary monocular 3D object detection that accepts text, point, and box prompts, and optionally incorporates depth cues at inference time. The model uses dual-vision encoders (image and RGBD) with a depth fusion module, a promptable detector, and a 3D detection head with unambiguous…

Weikai Huang, Jieyu Zhang, Sijun Li, Taoyang Jia, et al.
Published
Apr 2026
Citations
7
Code
606 stars
Read summary Original
13

arXiv.org

Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

Spatial-TTT is a framework for streaming visual-based spatial intelligence that uses test-time training (TTT) to maintain adaptive fast weights as a compact memory for accumulating 3D evidence from long-horizon videos. It employs a hybrid architecture interleaving TTT layers with self-attention anchor layers at a 3:1 ratio, large-chunk updates, and…

Fangfu Liu, Diankun Wu, Jiawei Chi, Yimo Cai, et al.
Published
Mar 2026
Citations
3
Code
249 stars
Read summary Original
14

arXiv.org

Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence

Holi-Spatial is a fully automated pipeline that converts raw video streams into holistic 3D spatial annotations without human intervention, addressing the scalability limits of existing spatial intelligence datasets that rely on manually annotated 3D scans. The pipeline has three stages: geometric optimization using 3D Gaussian Splatting (3DGS) with…

Yuanyuan Gao, Hao Li, Yifei Liu, Xinhao Ji, et al.
Published
Mar 2026
Citations
5
Code
373 stars
Read summary Original
15

arXiv.org

Utonia: Toward One Encoder for All Point Clouds

Utonia introduces a single self-supervised point transformer encoder trained jointly on diverse point cloud domains, including indoor scans, outdoor LiDAR, remote sensing, object CAD, and video-lifted point clouds. The authors identify three core cross-domain mismatches: inconsistent modality availability, sensitivity to granularity shifts, and bias toward…

Yujia Zhang, Xiaoyang Wu, Yunhan Yang, Xianzhe Fan, et al.
Published
Mar 2026
Citations
9
Code
717 stars
Read summary Original
16

Google DeepMind

LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

LoGeR (Long-context Geometric Reconstruction) is a novel architecture for scaling feedforward dense 3D reconstruction to extremely long video sequences (up to 19k frames) without post-optimization. It processes video in chunks, using bidirectional attention for intra-chunk reasoning and a hybrid memory module for inter-chunk coherence. The hybrid memory…

Junyi Zhang, Charles Herrmann, Junhwa Hur, Chen Sun, et al.
Published
Mar 2026
Citations
22
Code
609 stars
Read summary Original
17

arXiv.org

InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields

InfiniDepth introduces a novel depth representation that models depth as neural implicit fields, enabling arbitrary-resolution and fine-grained monocular depth estimation. The method uses a Vision Transformer encoder to extract multi-scale features, which are queried at continuous 2D coordinates via bilinear interpolation and fused hierarchically through a…

Hao Yu, Haotong Lin, Jiawei Wang, Jiaxin Li, et al.
Published
Jan 2026
Citations
12
Code
1.1K stars
Read summary Original
18

International Conference on 3D Vision

CaricatureGS: Exaggerating 3D Gaussian Splatting Faces With Gaussian Curvature

CaricatureGS introduces a method for creating photorealistic, controllable 3D caricature avatars by combining curvature-based geometric deformation with 3D Gaussian Splatting (3DGS). The pipeline starts with a multiview video, extracts a FLAME mesh, and solves a curvature-weighted Poisson equation to produce an exaggerated mesh. To train the 3DGS,…

Eldad Matmon, Amit Bracha, Noam Rotstein, Ron Kimmel
Published
Jan 2026
Citations
0
Code
Not linked
Read summary Original
19

arXiv.org

Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform

Visionary is an open, web-native platform for real-time rendering of 3D Gaussian Splatting (3DGS) and meshes, built on WebGPU and ONNX. It introduces a Gaussian Generator contract, a standardized ONNX I/O interface that allows plug-and-play integration of various 3DGS algorithms (e.g., MLP-based 3DGS, 4DGS, neural avatars) without modifying the renderer.…

Yuning Gong, Yifei Liu, Yifan Zhan, Muyao Niu, et al.
Published
Dec 2025
Citations
2
Code
517 stars
Read summary Original
20

Meta AI

SAM 3D: 3Dfy Anything in Images

SAM 3D is a generative model for 3D object reconstruction from a single image, predicting geometry, texture, and layout. It excels in natural images with occlusion and clutter, using a human- and model-in-the-loop pipeline to create large-scale 3D annotation data. The model uses a multi-stage training framework: synthetic pretraining on 2.7M meshes…

SAM 3D Team, Xingyu Chen, Fu-Jen Chu, Pierre Gleize, et al.
Published
Nov 2025
Citations
197
Code
7.2K stars
Read summary Original
21

arXiv.org

Part-X-MLLM: Part-aware 3D Multimodal Large Language Model

Part-X-MLLM is a native 3D multimodal large language model that unifies diverse 3D tasks by formulating them as programs in a structured, executable grammar. Given an RGB point cloud and a natural language prompt, the model autoregressively generates a token sequence encoding part-level bounding boxes, semantic descriptions, and edit commands. This…

Chunshi Wang, Junliang Ye, Yunhan Yang, Yang Li, et al.
Published
Nov 2025
Citations
5
Code
119 stars
Read summary Original
22

arXiv.org

Depth Anything 3: Recovering the Visual Space from Any Views

Depth Anything 3 (DA3) is a model that predicts spatially consistent geometry from any number of images, with or without known camera poses. It uses a single plain transformer (e.g., vanilla DINOv2) as backbone, with an input-adaptive cross-view self-attention mechanism and a dual-DPT head that jointly outputs depth and ray maps. A depth-ray representation…

Haotong Lin, Sili Chen, Junhao Liew, Donny Y. Chen, et al.
Published
Nov 2025
Citations
499
Code
6.1K stars
Read summary Original
23

arXiv.org

Visual Spatial Tuning

The paper introduces Visual Spatial Tuning (VST), a framework to enhance the spatial perception and reasoning abilities of Vision-Language Models (VLMs) without adding specialized 3D encoders. VST comprises two datasets: VST-P, with 4.1 million samples across 19 tasks covering single-image, multi-image, and video scenarios, and VST-R, with 135K samples for…

Rui Yang, Ziyu Zhu, Yanwei Li, Jingjia Huang, et al.
Published
Nov 2025
Citations
64
Code
201 stars
Read summary Original
24

arXiv.org

NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks

Nano3D is a training-free framework for 3D object editing that supports removal, addition, and replacement tasks without requiring masks. It integrates FlowEdit into the TRELLIS pipeline to perform localized edits guided by front-view renderings, and introduces region-aware merging strategies (Voxel/Slat-Merge) to preserve structural fidelity in unedited…

Junliang Ye, Shenghao Xie, Ruowen Zhao, Zhengyi Wang, et al.
Published
Oct 2025
Citations
27
Code
179 stars
Read summary Original
25

arXiv.org

FlashWorld: High-quality 3D Scene Generation within Seconds

FlashWorld is a generative model that creates 3D scenes from a single image or text prompt in seconds, being 10-100x faster than previous methods while achieving superior rendering quality. It shifts from the conventional multi-view-oriented (MV-oriented) paradigm to a 3D-oriented approach that directly produces 3D Gaussian representations during…

Xinyang Li, Tengfei Wang, Zixiao Gu, Shengchuan Zhang, et al.
Published
Oct 2025
Citations
26
Code
834 stars
Read summary Original
26

arXiv.org

From Editor to Dense Geometry Estimator

FE2E is a framework that adapts a pre-trained image editing model, Step1X-Edit, for monocular dense geometry prediction (depth and normal estimation). The authors argue that editing models, unlike text-to-image generators, possess inherent structural priors that make them more suitable for image-to-image tasks. They introduce three key adaptations: a…

JiYuan Wang, Chunyu Lin, Lei Sun, Rongying Liu, et al.
Published
Sep 2025
Citations
25
Code
243 stars
Read summary Original
27

arXiv.org

Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation

Droplet3D addresses 3D data scarcity by leveraging commonsense priors from videos for 3D generation. The authors introduce Droplet3D-4M, a large-scale dataset of 4 million 3D models, each with an 85-frame 360-degree orbital rendering video and dense multi-view-level text captions averaging 260 words. They also present Droplet3D, a generative model…

Xiaochuan Li, Guoguang Du, Runze Zhang, Liang Jin, et al.
Published
Aug 2025
Citations
2
Code
43 stars
Read summary Original
28

arXiv.org

MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

MeshCoder is a framework that reconstructs 3D objects from point clouds into editable Blender Python scripts. It introduces a set of expressive Blender Python APIs capable of modeling complex geometries beyond simple primitives, including primitives, translation, bridge loops, boolean operations, and arrays. A large-scale paired object-code dataset was…

Bingquan Dai, Li Ray Luo, Qihong Tang, Jie Wang, et al.
Published
Aug 2025
Citations
12
Code
501 stars
Read summary Original
29

IEEE International Conference on Computer Vision

LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

LongSplat is a framework for novel view synthesis from casually captured long videos without known camera poses. It jointly optimizes camera poses and 3D Gaussian Splatting (3DGS) to address pose drift, inaccurate geometry initialization, and memory limitations. Key components include incremental joint optimization, a pose estimation module using learned…

Chin-Yang Lin, Cheng Sun, Fu-En Yang, Min-Hung Chen, et al.
Published
Aug 2025
Citations
28
Code
799 stars
Read summary Original