Pith. sign in

Paper Citation Record · LEDGER

GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model

As of 17 July 2026, this Paper Citation Record lists 15 of 15 outbound references and 9 inbound Pith citation observations for arXiv:2604.03039.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2604.03039 v2

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-13T20:25:17.667260Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-17T06:31:00.352745+00:00

measured 9 of 9 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-29T18:18:26.276827Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-07-10T12:15:01.137692Z

Reference resolution

15 of 15 outbound references displayed

  • verified exact4
  • verified fuzzy11
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5b978d74-3b56-43e1-8e1c-ee0f544752ab · outbound

This paper cites Gc-gs: Gradient control gaussian splatting with various image degradation.

GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model Gc-gs: Gradient control gaussian splatting with various image degradation

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T01:43:38.935880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-13T20:25:17.667260Z digest=sha256:a1f2db4bbd48af2e9b45c2bdb467131d61f3e8518474b91ac29bdcf14af2d3e3

Observation a09013cf-fa6d-4691-879e-7fe5220c3ec4 · outbound

This paper cites Revitalizing convolutional network for image restoration.

GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model Revitalizing convolutional network for image restoration

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T01:43:38.926574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-13T20:25:17.667260Z digest=sha256:72eab1521e7f9d8cea5189df85bea58e6da1e6c9da1d888bd83dc06163352bf1

Observation 0c30237f-3d35-4ef2-b4f8-70c419b5d31a · outbound

This paper cites Luminance-gs: Adapting 3d gaussian splatting to chal- lenging lighting conditions with view-adaptive curve adjustment.

GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model Luminance-gs: Adapting 3d gaussian splatting to chal- lenging lighting conditions with view-adaptive curve adjustment

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T01:43:38.982347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-13T20:25:17.667260Z digest=sha256:5b80f6bc602558a265801d572e34284b935a88c135c61f4a573be624f83bd34e

Observation 20b907ba-5204-4944-837a-c4fc576f5997 · outbound

This paper cites Faster-gs: Analyzing and improv- ing gaussian splatting optimization.

GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model Faster-gs: Analyzing and improv- ing gaussian splatting optimization

Reference 4

Resolution
verified exact
arxiv_id, observed 2026-05-13T20:28:14.040114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-13T20:25:17.667260Z digest=sha256:2113b33bd2a242d42f11075b7cf3addb186518551bb66dcc06a4ed981d0a3935

Observation 86ffcb9d-8819-48e2-9cb7-d2302951de93 · outbound

This paper cites Single image haze removal using dark channel prior.IEEE transactions on pat- tern analysis and machine intelligence, 33(12):2341–2353.

GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model Single image haze removal using dark channel prior.IEEE transactions on pat- tern analysis and machine intelligence, 33(12):2341–2353

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T01:43:38.988056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-13T20:25:17.667260Z digest=sha256:ecd115314ee1bfdbd259b1f455a773d91bdde96a1a9add88b8f4e0dd34122aa4

Observation ff764d41-1a18-4e2a-b332-c4a89e2b1385 · outbound

This paper cites Sr- splat: Feed-forward super-resolution gaussian splatting from sparse multi-view images.

GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model Sr- splat: Feed-forward super-resolution gaussian splatting from sparse multi-view images

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T01:43:38.966425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-13T20:25:17.667260Z digest=sha256:11deab8457895c895e86a2365b99b94275fa14cd7c284b6d794b081fef32559c

Observation d4ab1592-b330-41f4-9738-471d0ad134aa · outbound

This paper cites 3d gaussian splatting for real-time radiance field rendering.ACM Trans.

GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model 3d gaussian splatting for real-time radiance field rendering.ACM Trans

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T01:43:38.919303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-13T20:25:17.667260Z digest=sha256:c6f4ec80ecc5b995482d757fee13f0d279d8f32697c73d7314dba45217a65cc7

Observation c0609879-4291-479a-b0ac-d5f330a367be · outbound

This paper cites 3d gaussian splat- ting as markov chain monte carlo.Advances in Neural Infor- mation Processing Systems, 37:80965–80986.

GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model 3d gaussian splat- ting as markov chain monte carlo.Advances in Neural Infor- mation Processing Systems, 37:80965–80986

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T01:43:39.003788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-13T20:25:17.667260Z digest=sha256:d41c442a3072df5da367b97ca6204ff1c2352a8850ec075abc507d92f647b96f

Observation 21a6fab6-c431-457a-9761-1aab1c72e92a · outbound

This paper cites Seathru- nerf: Neural radiance fields in scattering media.

GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model Seathru- nerf: Neural radiance fields in scattering media

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T01:43:38.930167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-13T20:25:17.667260Z digest=sha256:c8a7c7791e42c1fbd33e4fe6f9727457f076ab81766487431d64560644ae7653

Observation 004b23d9-eca7-47c5-b7ca-54c421b96428 · outbound

This paper cites Realx3d: A physically-degraded 3d benchmark for multi-view visual restoration and recon- struction.

GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model Realx3d: A physically-degraded 3d benchmark for multi-view visual restoration and recon- struction

Reference 10

Resolution
verified exact
arxiv_id, observed 2026-05-13T20:28:14.034411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-13T20:25:17.667260Z digest=sha256:e85812f49ee02ac704270e0a57070c3a11cd88353183d838a748611bc4c4a7bb

Observation 1febe554-352f-42d8-bbe8-305c80f697c4 · outbound

This paper cites I2-nerf: Learning neural radiance fields un- der physically-grounded media interactions.

GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model I2-nerf: Learning neural radiance fields un- der physically-grounded media interactions

Reference 11

Resolution
verified exact
arxiv_id, observed 2026-05-13T20:28:14.037517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-13T20:25:17.667260Z digest=sha256:92262ae78439c6f077245a9f8ad3eee664bc2d6ac52acbe716bd4d3350082bce

Observation aa828a20-6452-421b-bb46-227cf2e8ab3d · outbound

This paper cites OpenAI: GPT-Image-1.5.https://openai.

GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model OpenAI: GPT-Image-1.5.https://openai

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T01:43:38.939241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-13T20:25:17.667260Z digest=sha256:f308d44730d1fbb7009498db1a400b52818dd48b18a038f80563849670ca30ee

Observation 06800075-80a6-44a3-91b8-c69308949b2e · outbound

This paper cites Seasplat: Representing underwater scenes with 3d gaussian splatting and a physically grounded image formation model.

GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model Seasplat: Representing underwater scenes with 3d gaussian splatting and a physically grounded image formation model

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T01:43:38.998928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-13T20:25:17.667260Z digest=sha256:53b56920e91f9aa95c035f566529c820762f617432ae5bf5b47caf98277a7a6b

Observation 861045b8-807c-416f-bbb6-dcda77ccbcd8 · outbound

This paper cites Lita-gs: Illumination- agnostic novel view synthesis via reference-free 3d gaus- sian splatting and physical priors.

GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model Lita-gs: Illumination- agnostic novel view synthesis via reference-free 3d gaus- sian splatting and physical priors

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T01:43:38.915276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-13T20:25:17.667260Z digest=sha256:7e0bd0ce54d864b5d31d748af6967d65fc6b64fbcfe245072a13882d59fcedc4

Observation 1edaabd4-013c-4cd5-a1bd-12a88d4582c2 · outbound

This paper cites Udpnet: Unleashing depth-based priors for robust image de- hazing.

GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model Udpnet: Unleashing depth-based priors for robust image de- hazing

Reference 15

Resolution
verified exact
arxiv_id, observed 2026-05-13T20:28:14.031674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-13T20:25:17.667260Z digest=sha256:00c7642252c05ccfccf360c6d093a9d6f089bd9b842a5205831a390260f3deb5

Pith citing papers

Observation efa16575-b1c9-4124-89a9-3fb25efb25ed · inbound

NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results cites this paper.

NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model

Reference 4

Resolution
verified exact
local_arxiv, observed 2026-05-13T17:08:01.830210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-13T16:54:34.457273Z digest=sha256:a759af5c718deca50af29b0e9cb060d6e459e3ad799a7a6a4e25e65ee6ffa348

Observation 298856d2-cf49-4430-af2b-293f2dcc9baf · inbound

SmokeGS-R: Physics-Guided Pseudo-Clean 3DGS for Real-World Multi-View Smoke Restoration cites this paper.

SmokeGS-R: Physics-Guided Pseudo-Clean 3DGS for Real-World Multi-View Smoke Restoration GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model

Reference 1

Resolution
verified exact
local_arxiv, observed 2026-05-11T00:00:56.085436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-10T18:44:16.161453Z digest=sha256:a4b58a40e485d3db27ae3f7c923ce82ebe44ccfd510b4d0122de4f8e28f56a89

Observation 86fc9cbc-e64f-42e5-be1f-f145b34cac51 · inbound

CLIP-Guided Data Augmentation for Night-Time Image Dehazing cites this paper.

CLIP-Guided Data Augmentation for Night-Time Image Dehazing GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model

Reference 10

Resolution
verified exact
local_arxiv, observed 2026-05-11T00:25:49.817444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-10T18:33:51.064583Z digest=sha256:4b24e64515f84f34e00f139f367854458fd3ba9cef457a298eb27a6a1d3f5e4d

Observation fc5b4039-fa5c-4962-829a-93c3fb2e1b47 · inbound

3D Smoke Scene Reconstruction Guided by Vision Priors from Multimodal Large Language Models cites this paper.

3D Smoke Scene Reconstruction Guided by Vision Priors from Multimodal Large Language Models GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model

Reference 4

Resolution
verified exact
local_arxiv, observed 2026-05-10T22:35:49.039181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-10T19:44:10.507760Z digest=sha256:f357570e00ba37d79a02da3fb5673e422c5cd1db698d58ba48c9e96ae1550312

Observation 926d3fad-9934-424f-956a-09f6640e6165 · inbound

Dual-Branch Remote Sensing Infrared Image Super-Resolution cites this paper.

Dual-Branch Remote Sensing Infrared Image Super-Resolution GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model

Reference 2

Resolution
verified exact
local_arxiv, observed 2026-05-11T09:31:03.726523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-10T15:59:13.110096Z digest=sha256:4301f4f9c611867407339779d3d1d244f31aaa4d42bf06669abde483d8eb4663

Observation 7ae345e1-b528-4040-827b-49507b68e503 · inbound

Beyond Model Design: Data-Centric Training and Self-Ensemble for Gaussian Color Image Denoising cites this paper.

Beyond Model Design: Data-Centric Training and Self-Ensemble for Gaussian Color Image Denoising GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model

Reference 12

Resolution
verified exact
local_arxiv, observed 2026-05-11T11:21:01.267206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-10T15:00:54.721762Z digest=sha256:ccf898bc8265808f8eb6a838cb6d58b709df0f706c7e4294309686d2d4fcb8e9

Observation 241d3c47-98aa-4de1-8d76-f0c39b0562de · inbound

Training-Free Model Ensemble for Single-Image Super-Resolution via Strong-Branch Compensation cites this paper.

Training-Free Model Ensemble for Single-Image Super-Resolution via Strong-Branch Compensation GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model

Reference 3

Resolution
verified exact
local_arxiv, observed 2026-05-11T09:21:01.967462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-10T16:04:24.442890Z digest=sha256:cda4a0a7d61cbddaf55b89d7843f88409deb0402a1ffe75ef98ecc8f9a13037b

Observation 857a2b6e-f7c7-432c-98ee-3fa72d884b5d · inbound

Dehaze-then-Splat: Generative Dehazing with Physics-Informed 3D Gaussian Splatting for Smoke-Free Novel View Synthesis cites this paper.

Dehaze-then-Splat: Generative Dehazing with Physics-Informed 3D Gaussian Splatting for Smoke-Free Novel View Synthesis GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model

Reference 9

Resolution
verified exact
local_arxiv, observed 2026-05-10T13:30:26.434780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-05-10T13:29:35.398568Z digest=sha256:c09fe69b990739a0cef12cb501d27abdc10616608e441a4cf0e332433acf0fa6

Observation 5e0c8373-acf0-4961-b467-fdb18948d850 · inbound

DelowlightSplat: Feed-Forward Gaussian Splatting for Lowlight 3D Scene Reconstruction cites this paper.

DelowlightSplat: Feed-Forward Gaussian Splatting for Lowlight 3D Scene Reconstruction GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model

Reference 9

Resolution
verified exact
local_arxiv, observed 2026-06-29T18:23:50.260155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-17T06:31:00.352745+00:00.

source=pdf_text observed=2026-06-29T18:18:26.276827Z digest=sha256:827e2b09bcf9de3dd62043eb741d90e04ec1a3a1ffb64cb02a326d00200a2bf9