2026-08-14 04:00 UTCOriginal source2 min readUpdated: 2026-08-14 09:14 UTC

MV2: Multi-View Multi-Vehicle Driving Dataset for Novel View Synthesis

MV2 introduces a multi-view, multi-vehicle driving dataset and benchmark for evaluating novel view synthesis under large viewpoint changes in dynamic urban scenes. It provides 50 high-quality scenes and 12,000 synchronized images captured from a car, scooter, and drone. Benchmarking shows NVS quality degrades as viewpoint disparity grows, and feed-forward pose estimators lag optimization-based methods. Dataset and benchmark resources are publicly available.

SourcearXiv Computer VisionAuthor: Sanjay Bhargav Dharavath, Hanvitha Saraswathi Mukkamala, Faizan Farooq Khan, Ioannis Kakogeorgiou, Aditya Arun, C V Jawahar, Zakaria Laskar

Article intelligence

InvestorsAdvanced

Key points

MV2 provides synchronized car, scooter, and drone captures to support NVS evaluation under much larger viewpoint changes than single-trajectory datasets.
The dataset includes 50 high-quality scenes and 12,000 images, registered with SfM and verified via manual pixel-level correspondences.
Benchmarks show NVS quality degrades with viewpoint disparity, and feed-forward pose estimators significantly trail optimization-based methods.
The dataset, benchmark protocol, and resources are available on the project website; the paper is accepted at ECCV.

Why it matters

This matters because mV2 provides synchronized car, scooter, and drone captures to support NVS evaluation under much larger viewpoint changes than single-trajectory datasets.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

This panel is AI-generated and reviewed for accuracy.

-->

[Submitted on 12 Aug 2026]

Title:MV2: Multi-View Multi-Vehicle Driving Dataset for Novel View Synthesis

View a PDF of the paper titled MV2: Multi-View Multi-Vehicle Driving Dataset for Novel View Synthesis, by Sanjay Bhargav Dharavath and 5 other authors

View PDF HTML (experimental)

Abstract:Differentiable rendering has advanced novel view synthesis (NVS), yet applying it to real-world driving remains difficult due to sparse capture viewpoints, dynamic objects, and limited multi-trajectory data. We introduce the Multi-View Multi-Vehicle (MV2) dataset and benchmark for evaluating NVS models under large viewpoint changes in dynamic urban scenes. MV2 features synchronized captures from a car, scooter, and drone, each following distinct yet synchronized trajectories. Training NVS methods on one vehicle's camera stream and testing on another enables evaluation under substantially larger viewpoint variations than existing single-trajectory datasets. All sequences are registered via Structure-from-Motion and camera poses verified using manual pixel-level correspondence annotations, yielding 50 high-quality scenes with 12000 images. Benchmarking recent NVS and camera pose estimation methods shows that NVS performance degrades with increasing viewpoint disparity, and that feed-forward pose estimators notably lag behind optimization-based approaches, highlighting MV2 as a rigorous testbed for NVS in driving. The dataset, benchmark protocol, and project resources are available at this https URL.

Comments: 18 pages, 7 figures, ECCV accepted paper

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2608.12442 [cs.CV]

(or arXiv:2608.12442v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2608.12442

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Sanjay Bhargav Dharavath [view email] [v1] Wed, 12 Aug 2026 16:02:32 UTC (53,980 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled MV2: Multi-View Multi-Vehicle Driving Dataset for Novel View Synthesis, by Sanjay Bhargav Dharavath and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-08

Change to browse by:

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)